#+TITLE: Lecturas 
#+OPTIONS: ^:nil

Este repositorio es una recopilación de lecturas.

* Contenido :TOC:

- [[#lecturas-del-year-2025][Lecturas del year 2025]]
  - [[#diciembre-2025][Diciembre 2025]]
  - [[#noviembre-2025][Noviembre 2025]]
  - [[#octubre-2025][Octubre 2025]]
  - [[#septiembre-2025][Septiembre 2025]]
  - [[#agosto-2025][Agosto 2025]]
  - [[#julio-2025][Julio 2025]]
  - [[#junio-2025][Junio 2025]]
  - [[#mayo-2025][Mayo 2025]]
  - [[#abril-2025][Abril 2025]]
  - [[#marzo-2025][Marzo 2025]]
  - [[#febrero-2025][Febrero 2025]]
  - [[#enero-2025][Enero 2025]]
- [[#lecturas-del-year-2024][Lecturas del year 2024]]
  - [[#diciembre-2024][Diciembre 2024]]
  - [[#noviembre-2024][Noviembre 2024]]
  - [[#octubre-2024][Octubre 2024]]
  - [[#septiembre-2024][Septiembre 2024]]
  - [[#agosto-2024][Agosto 2024]]
  - [[#julio-2024][Julio 2024]]
  - [[#junio-2024][Junio 2024]]
  - [[#mayo-2024][Mayo 2024]]
  - [[#abril-2024][Abril 2024]]
  - [[#marzo-2024][Marzo 2024]]
  - [[#febrero-2024][Febrero 2024]]
  - [[#enero-2024][Enero 2024]]
- [[#lecturas-del-year-2023][Lecturas del year 2023]]
  - [[#diciembre-2023][Diciembre 2023]]
  - [[#noviembre-2023][Noviembre 2023]]
  - [[#octubre-2023][Octubre 2023]]
  - [[#septiembre-2023][Septiembre 2023]]
  - [[#agosto-2023][Agosto 2023]]
  - [[#julio-2023][Julio 2023]]
  - [[#junio-2023][Junio 2023]]
  - [[#mayo-2023][Mayo 2023]]
  - [[#abril-2023][Abril 2023]]
  - [[#marzo-2023][Marzo 2023]]
  - [[#febrero-2023][Febrero 2023]]
  - [[#enero-2023][Enero 2023]]
- [[#lecturas-del-year-2022][Lecturas del year 2022]]
  - [[#diciembre-2022][Diciembre 2022]]
  - [[#noviembre-2022][Noviembre 2022]]
  - [[#octubre-2022][Octubre 2022]]
  - [[#septiembre-2022][Septiembre 2022]]
  - [[#agosto-2022][Agosto 2022]]
  - [[#julio-2022][Julio 2022]]
  - [[#junio-2022][Junio 2022]]
  - [[#mayo-2022][Mayo 2022]]
  - [[#abril-2022][Abril 2022]]
  - [[#marzo-2022][Marzo 2022]]
  - [[#febrero-2022][Febrero 2022]]
  - [[#enero-2022][Enero 2022]]
- [[#lecturas-del-year-2021][Lecturas del year 2021]]
  - [[#diciembre-2021][Diciembre 2021]]
  - [[#noviembre-2021][Noviembre 2021]]
  - [[#octubre-2021][Octubre 2021]]
  - [[#septiembre-2021][Septiembre 2021]]
  - [[#agosto-2021][Agosto 2021]]
  - [[#julio-2021][Julio 2021]]
  - [[#junio-2021][Junio 2021]]
  - [[#mayo-2021][Mayo 2021]]
  - [[#abril-2021][Abril 2021]]
  - [[#marzo-2021][Marzo 2021]]
  - [[#febrero-2021][Febrero 2021]]
  - [[#enero-2021][Enero 2021]]
- [[#lecturas-del-year-2020][Lecturas del year 2020]]
  - [[#diciembre-2020][Diciembre 2020]]
  - [[#noviembre-2020][Noviembre 2020]]
  - [[#octubre-2020][Octubre 2020]]
  - [[#septiembre-2020][Septiembre 2020]]
  - [[#agosto-2020][Agosto 2020]]
  - [[#julio-2020][Julio 2020]]
  - [[#junio-2020][Junio 2020]]
  - [[#mayo-2020][Mayo 2020]]
  - [[#abril-2020][Abril 2020]]
  - [[#marzo-2020][Marzo 2020]]
  - [[#febrero-2020][Febrero 2020]]
  - [[#enero-2020][Enero 2020]]
- [[#lecturas-del-year-2019][Lecturas del year 2019]]
  - [[#diciembre-2019][Diciembre 2019]]
  - [[#noviembre-2019][Noviembre 2019]]
  - [[#octubre-2019][Octubre 2019]]
  - [[#septiembre-2019][Septiembre 2019]]


* Lecturas del year 2025

** Diciembre 2025

+ [[https://huggingface.co/blog/neuml/biomedbert-hash-nano][Encoding the World's Medical Knowledge into 970K]] #Embedding #Medical
+ [[https://blog.roboflow.com/rf-detr/][RF-DETR: A SOTA Real-Time Object Detection Model]] #ObjectDetection
+ [[https://sihanxu.me/nepa/][Next-Embedding Prediction Makes Strong Vision Learners]] #pretraining #optretina
+ [[Gemma Scope 2: helping the AI safety community deepen understanding of complex language model behavior][Gemma Scope 2: helping the AI safety community deepen understanding of complex language model behavior]] #Interpretability #LLMs
+ [[https://hms.harvard.edu/news/researchers-discover-bias-ai-models-analyze-pathology-samples][Researchers Discover Bias in AI Models That Analyze Pathology Samples]] #Pathology #Bruno #Bias
+ [[https://www.nature.com/articles/s41746-025-01751-7][A cross population study of retinal aging biomarkers with longitudinal pre-training and label distribution learning]] #Elena #UPRetina
+ [[https://docs.unsloth.ai/new/deploy-llms-phone][How to Run and Deploy LLMs on your iOS or Android Phone]] #Phone #LLMs
+ [[https://huggingface.co/blog/tokenizers][Tokenization in Transformers v5: Simpler, Clearer, and More Modular]] #Tokenizers
+ [[https://elite-ai-assisted-coding.dev/p/most-rag-systems-have-a-context-problem][Most RAG systems have a context problem]] #RAG #Pablo
+ [[https://escueladoctorado.unizar.es/sites/escueladoctorado/files/users/docto/docs/IA/jorbienvenidaeduz_24-25_conferenciaia_ana_gracia-gil.pdf][IA en la investigación doctoral: oportunidades, límites y responsabilidad]] #IA #Doctorado
+ [[https://ai.meta.com/samaudio/][Introducing Meta Segment Anything Model Audio (SAM Audio)]] #Audio #Segmentation
+ [[https://huggingface.co/blog/eurollm-team/eurollm-22b][EuroLLM-22B]] #ChistERA
+ [[https://huggingface.co/blog/nvidia/nemotron-3-nano-efficient-open-intelligent-models][Nemotron 3 Nano - A new Standard for Efficient, Open, and Intelligent Agentic Models Enterprise + Article]] #Agents
+ [[https://allenai.org/blog/bolmo][Introducing Bolmo: Byteifying the next generation of language models]] #LLM #ByteTokenizer
+ [[https://research.google/blog/a-differentially-private-framework-for-gaining-insights-into-ai-chatbot-use/][A differentially private framework for gaining insights into AI chatbot use]] #Privacy #Chatbots
+ [[https://huggingface.co/spaces/OpenEvals/evaluation-guidebook][The LLM Evaluation Guidebook]] #Júlia #Evaluation 
+ [[https://www.cell.com/cell-reports-medicine/fulltext/S2666-3791(25)00549-X][An integrated language-vision foundation model for conversational diagnostics and triaging in primary eye care]] #Elena #optretina
+ [[https://huggingface.co/blog/nvidia/custom-policy-reasoning-nemotron-content-safety][Custom Policy Enforcement with Reasoning: Faster, Safer AI Applications]] #Pablo #safety
+ [[https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_ministral3_vl.ipynb][Supervised Fine-Tuning (SFT) Ministral-3 with QLoRA using TRL]] #OPTRetina #Elena
+ [[https://arxiv.org/abs/2507.10492][BenchReAD: A Systematic Benchmark for Retinal Anomaly Detection]] #AnomalyDetection #OPTRetina #SpectralGeo
+ [[https://www.nature.com/articles/s41598-025-25091-4][Large-scale remote sensing model enables an integrated monitoring approach for high-resolution tracking pest vole populations]] #ImagenAerea #Adrián #Galicia

+ [[https://github.com/neuml/paperetl][neuml/paperetl: 📄 ⚙️ ETL processes for medical and scientific papers]] #Medicine
+ [[https://sophont.med/blog/medmarks#introduction][Medmarks v0.1, a new LLM benchmark suite of medical tasks]] #Medical #LLM #Benchmark
+ [[https://blog.google/technology/developers/t5gemma-2/][T5Gemma 2: The next generation of encoder-decoder models]] #Multimodal #Elena
+ [[https://docs.unsloth.ai/models/functiongemma][FunctionGemma: How to Run & Fine-tune | Unsloth Documentation]] #FunctionCalling #Júlia
+ [[https://apigen-pipeline.github.io/][APIGen Pipeline]] #FunctionCalling #Júlia #API
** Noviembre 2025

+ [[http://lse-sign.bcbl.eu/web-busqueda/][LSE-Sign]] #LSEAvatar
+ [[https://huggingface.co/blog/continuous_batching][Continuous batching]] #LLM #Optimization
+ [[https://huggingface.co/blog/flux-2][Welcome FLUX.2 - BFL’s new open image generation model 🤗]] #ImageGeneration
+ [[https://arxiv.org/abs/2506.01942][OD3: Optimization-free Dataset Distillation for Object Detection]] #DatasetDistillation #Joaquin
+ [[https://github.com/Guang000/Awesome-Dataset-Distillation][Awesome Dataset Distillation]] #DatasetDistillation #Joaquin
+ [[https://arxiv.org/pdf/2204.08499][DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning]] #DataPruning #Joaquin
+ [[https://arxiv.org/abs/240161][Coreset Selection for Object Detection]] #DataPruning #Joaquin
+ [[https://dl.acm.org/doi/10.1145/3664647.3681592][Evolution-aware VAriance (EVA) Coreset Selection for Medical Image Classification]] #DataPruning #Joaquin
+ [[https://www.arxiv.org/pdf/2503.00828][Training-Free Dataset Pruning for Instance Segmentation]] #DataPruning #Joaquin
+ [[https://aclanthology.org/2024.signlang-1.43.pdf][SignaMed: a Cooperative Bilingual LSE-Spanish Dictionary in the Healthcare Domain]] #LenguaSignos
+ [[https://link.springer.com/article/10.1007/s00521-024-10776-0#Fun][A real-time platform for Spanish Sign Language interpretation]] #LenguaSignos
+ [[https://openreview.net/forum?id=GMR9BUsPbq][BANZ-FS: BANZSL Fingerspelling Dataset]] #LenguaSignos
+ [[https://huggingface.co/microsoft/llava-med-v1.5-mistral-7b][LLaVA-Med]] #Elena
+ [[https://github.com/snap-stanford/med-flamingo/tree/master][Med-Flamingo]] #Elena
+ [[https://ai.google.dev/gemma/docs/core/huggingface_vision_finetune_qlora][Fine-Tune Gemma for Vision Tasks using Hugging Face Transformers and QLoRA]] #OPTRetina
+ [[https://arxiv.org/abs/2505.02830][AOR: Anatomical Ontology-Guided Reasoning for Medical Large Multimodal Model in Chest X-Ray Interpretation]] #Elena
+ [[https://jitinjami.github.io/stratify/index.html][Stratify or Die: Rethinking Data Splits in Image Segmentation]] #Segmentation #Joaquin
+ [[https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_1121/paper.pdf][MIAS-SAM: Medical Image Anomaly Segmentation without thresholding]] #AnomalyDetection #SpectralGeo
+ [[https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_1015/paper.pdf][In-Model Merging for Enhancing the Robustness of Medical Imaging Classification Models]] #Joaquin #Adrian
+ [[https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_502/paper.pdf][DefectGPT: Towards Multi-Class Defect Detection with Limited Electrical Samples]] #AnomalyDetection #SpectralGeo
+ [[https://arxiv.org/abs/2310.18961][Anomalyclip: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection]] #AnomalyDetection #SpectralGeo
+ [[https://research.google/blog/real-time-speech-to-speech-translation/][Real-time speech-to-speech translation]] #Speech2Speech
+ [[https://arxiv.org/abs/2410.04201][Idempotent Test-Time Training]] #OOD
+ [[https://allenai.org/blog/olmo3][Olmo 3: Charting a path through the model flow to lead open-source AI]] #LLMs #Pablo
+ [[https://huggingface.co/blog/open-asr-leaderboard][Open ASR Leaderboard: Trends and Insights with New Multilingual & Long-Form Tracks]] #ASR #Sara
+ [[https://huggingface.co/blog/rapidfireai][20x Faster TRL Fine-tuning with RapidFire AI]] #Joaquin
+ [[https://sophont.med/blog/openmidnight#introduction][How to Train a State-of-the-Art Pathology Foundation Model with $1.6k]] #Bruno
+ [[https://ai.meta.com/blog/sam-3d/][Introducing SAM 3D: Powerful 3D Reconstruction for Physical World Images]] #LSEAvatar
+ [[https://ai.meta.com/blog/segment-anything-model-3/][Introducing Meta Segment Anything Model 3 and Segment Anything Playground]] #SemanticSegmentation #Adrian #Joaquin
+ [[https://link.springer.com/article/10.1007/s10579-024-09751-x#Sec14][Spoken Spanish PoS tagging: gold standard dataset]] #Sara
+ [[https://github.com/roboflow/notebooks?tab=readme-ov-file][roboflow notebooks]] #ComputerVision #Notebooks
+ [[https://huggingface.co/blog/mlabonne/merge-models][Merge Large Language Models with mergekit]] #ModelSoups #Joaquin
+ [[https://huggingface.co/merve/smol-vision/blob/main/Image_Search_with_MetaCLIP2.ipynb][Use MetaCLIP2 for Image Search]] #ImageSearch #Embeddings
+ [[https://github.com/Liquid4All/cookbook/tree/main/examples/car-maker-identification][Fine tuning LFM2-VL to identify car makers from images]] #LORA #VLM #OPTRetina
+ [[https://weaviate.io/blog/muvera][More efficient multi-vector embeddings with MUVERA]] #Embedding #RAG
+ [[https://github.com/OpenGVLab/efficient-video-recognition][Frozen CLIP models are Efficient Video Learners]] #VideoClassification #Maria
+ [[https://arxiv.org/pdf/2511.00916][Fleming-VL: Towards Universal Medical Visual Understanding with Multimodal LLMs]] #MLLM #Elena #Maria
+ [[https://github.com/emo-box/EmoBox][EmoBox]] #AnalisisSentimientos #Sara #Audio
+ [[https://github.com/FunAudioLLM/SenseVoice][SenseVoice]] #AnalisisSentimientos #Sara #Audio
+ [[https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_trl_lora_qlora.ipynb][Supervised Fine-Tuning (SFT) with LoRA/QLoRA using TRL — on a Free Colab Notebook]] #FineTuning #LORA
+ [[https://peerj.com/articles/cs-3112/#p-10][SignVLM: a pre-trained large video model for sign language recognition]] #LenguaSignos
+ [[https://magazine.sebastianraschka.com/p/beyond-standard-llms][Beyond Standard LLMs]] #LLMs
+ [[https://contextual.ai/blog/rerank-v2][Open-Sourcing Reranker v2]] #RAG #Retrieval
+ [[https://www.sciencedirect.com/science/article/pii/S2352711025003978][WATCHED: A Web AI Agent Tool for Combating Hate speech by Expanding Data]] #Agents #HateSpeech #Software
+ [[https://allenai.org/blog/olmoearth][Introducing OlmoEarth Platform: Powerful open infrastructure for planetary insights]] #Adrian #SatelliteImaging
+ [[https://deepmind.google/models/gemma/medgemma/][MedGemma: A Gemma 3 variant optimized for medical text and image comprehension.]] #Elena

** Octubre 2025

+ [[https://huggingface.co/docs/trl/main/example_overview][TFL VLM examples]] #OPTRetina #Elena
+ [[https://arxiv.org/abs/2510.01171][Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity]] #Prompting #Júlia
+ [[https://arxiv.org/abs/2305.06590][FactKG: Fact Verification via Reasoning on Knowledge Graphs]] #FactChecking
+ [[https://arxiv.org/abs/2510.24702][Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents]] #Júlia #Dataset
+ [[https://openai.com/index/introducing-gpt-oss-safeguard/][Introducing gpt-oss-safeguard]] #Safety #Pablo
+ [[https://huggingface.co/blog/voice-consent-gate][Voice Cloning with Consent]] #VoiceCloning #Ethics
+ [[https://www.liquid.ai/blog/lfm2-colbert-350m-one-model-to-embed-them-all][LFM2-ColBERT-350M: One Model to Embed Them All]] #Embedding #MultiLingual
+ [[https://martinfowler.com/articles/agentic-ai-security.html][Agentic AI and Security]] #Agents #Security #ProyectoNacional
+ [[https://arxiv.org/abs/2510.19806][The Art of Asking: Multilingual Prompt Optimization for Synthetic Data]] #SyntheticData  #Júlia #Multilingual
+ [[https://huggingface.co/blog/aisheets-unlock-images][Unlock the power of images with AI Sheets]] #Datasets
+ [[https://arxiv.org/abs/2505.07891v2][TrumorGPT: Graph-Based Retrieval-Augmented Large Language Model for Fact-Checking]] #FactChecking #CienciaEnClaro #GraphRAG
+ [[https://docs.camel-ai.org/cookbooks/data_generation/data_gen_with_real_function_calls_and_hermes_format][Real Function Calls and Hermes Format Data Generation]] #Camel #Júlia
+ [[https://research.google/blog/a-pictures-worth-a-thousand-private-words-hierarchical-generation-of-coherent-synthetic-photo-albums/][A picture's worth a thousand (private) words: Hierarchical generation of coherent synthetic photo albums]] #SyntheticData
+ [[https://research.google/blog/the-anatomy-of-a-personal-health-agent/][The anatomy of a personal health agent]] #Agents
+ Host Your Own Ollama Models for Free in [[https://medium.com/data-science-collective/create-a-remote-llm-server-using-kaggle-notebooks-and-ollama-acb299ead1e5][Kaggle]] and in [[https://medium.com/data-science-collective/unleash-the-power-of-ai-host-your-own-ollama-models-for-free-with-google-colab-0aac5f237a9f][Colab]] #Ollama
+ [[https://arxiv.org/abs/2402.18041][Datasets for Large Language Models: A Comprehensive Survey]] #Júlia #Dataset 
+ [[https://www.iic.uam.es/procesamiento-del-lenguaje-natural/creacion-de-corpus-orientados-a-sistemas-rag-y-su-uso-en-evaluacion/][Creación de corpus orientados a sistemas RAG y su uso en evaluación]] #Júlia #Dataset #RAG
+ [[https://arxiv.org/abs/2506.09147][LLM-as-a-qualitative-judge: automating error analysis in natural language generation]] #LLMasJudge
+ [[https://www.nature.com/articles/s41550-025-02670-z#data-availability][Textual interpretation of transient image classifications from large language models]] #FewShotLearning #OPTRetina
+ [[https://research.google/blog/a-collaborative-approach-to-image-generation/][A collaborative approach to image generation]] #ImageGeneration #Agent
+ [[https://arxiv.org/pdf/2510.03458][Omni-Embed-Nemotron: A Unified Multimodal Retrieval Model for Text, Image, Audio, and Video]] #MultiModalRetrieval
+ [[https://alexzhang13.github.io/blog/2025/rlm/][Recursive Language Models]] #LLMs
+ [[http://huggingface.co/blog/prithivMLmods/image-guard-models][Image-Guard-2.0: A SigLIP 2 Based Image Safety Classification Model]] #ImageGuard
+ [[https://www.modaic.dev/us][Building the Hugging Face for AI Agents]] #DSPY
+ [[https://www.sciencedirect.com/science/article/pii/S0925231225021423][Heterogeneous federated semantic segmentation]] #ModelSoup #FederatedLearning #Joaquin
+ [[https://github.com/ubc-tea/FedSoup/tree/main][FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation]] #ModelSoup #FederatedLearning #Joaquin
+ [[https://gregorygundersen.com/blog/2025/10/01/large-language-models/][A History of Large Language Models]] #LLMs
+ [[https://arxiv.org/abs/2406.15627][Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph]] #ChistERA #Pablo #Hallucinations
+ [[https://smithery.ai/][Your Agent's Gateway to the World]] #MCP #Júlia
+ [[https://civio.es/sanidad/2025/10/09/cuando-tu-medica-es-una-ia/][Cuando tu médica es una IA]] #CIAIS
+ [[https://blog.langchain.com/query-transformations/][Query Transformations]] #Pablo #RAG #QueryTransformation
+ [[https://medium.com/@adityabbsharma/unlocking-the-power-of-query-transformation-in-retrieval-augmented-generation-rag-fbe461c354d6][Unlocking the Power of Query Transformation in Retrieval-Augmented Generation (RAG)]] #Pablo #RAG #QueryTransformation
+ [[https://arxiv.org/pdf/2503.10654][Improving RAG Retrieval via Propositional Content Extraction: a Speech Act Theory Approach]] #Pablo #RAG #Propositions
+ [[https://arxiv.org/abs/2312.06648][Dense X Retrieval: What Retrieval Granularity Should We Use?]] #Pablo #PrevenIA #Retrieval
+ [[https://arxiv.org/abs/2509.04492][Learned Hallucination Detection in Black-Box LLMs using Token-level Entropy Production Rate]] #Hallucination #Pablo #PrevenIA
+ [[https://www.lesswrong.com/posts/bALBxf3yGGx4bvvem/prompt-optimization-can-enable-ai-control-research][Prompt optimization can enable AI control research]] #DSPY #Safety
+ [[https://arxiv.org/pdf/2509.20328][Video models are zero-shot learners and reasoners]] #VideoModels #FoundationalModel
+ [[https://arxiv.org/abs/2510.01179][TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments]] #Júlia #Dataset #ToolCalling
+ [[https://huggingface.co/blog/paultltc/modernvbert][ModernVBERT: Towards Smaller Visual Document Retrievers]] #Retrieval #VisualEncoder
+ [[https://thinkingmachines.ai/blog/lora/][LoRA Without Regret]]  #TFM #Elena #Fine-tuning
+ [[https://huggingface.co/docs/trl/main/en/lora_without_regret][LoRA Without Regret]] #TFM #Elena #Fine-tuning
+ [[https://huggingface.co/blog/rteb][Introducing RTEB: A New Standard for Retrieval Evaluation]] #Retrieval #Júlia
+ [[https://arxiv.org/abs/2502.13595][MMTEB: Massive Multilingual Text Embedding Benchmark]] #Dataset #Embeddings #Júlia

** Septiembre 2025

+ [[https://arxiv.org/pdf/2509.18234][The Illusion of Readiness: Stress Testing Large Frontier Models on Multimodal Medical Benchmarks]] #MultiModal #Medical #Benchmark
+ [[https://huggingface.co/blog/catherinearnett/in-defense-of-tokenizers][There is no such thing as a tokenizer-free lunch]] #Tokenizers
+ [[https://huggingface.co/papers/2509.20354][EmbeddingGemma: Powerful and Lightweight Text Representations]] #embeddings #Pablo #chistera
+ [[https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/basketball-ai-how-to-detect-track-and-identify-basketball-players.ipynb#scrollTo=aS25QDv1a8_W][Basketball AI: How to Detect, Track, and Identify Basketball Players]] #Detection #Tracking #VLMs
+ [[https://qwen.ai/blog?id=e199227023e8ebaac5f348f97fa804d1858ffc8a&from=research.research-list][Qwen3 ASR: Hear clearly, transcribe smartly]] #ASR #Chistera
+ [[https://qwen.ai/blog?id=f0bbad0677edf58ba93d80a1e12ce458f7a80548&from=research.research-list][Qwen3Guard: Real-time Safety for Your Token Stream]] #Guardrails #Pablo #PrevenIA
+ [[https://mistral.ai/news/magistral][Stands to reason. Magistral]] #chistera #Júlia 
+ [[https://www.hcompany.ai/blog/holo-1-5][Holo1.5 - Open Foundation Models for Computer Use Agents]] #Agents #ComputerUse
+ [[https://www.math.inc/gauss][Introducing Gauss, an agent for autoformalization]] #Formalisation
+ [[https://amaarora.github.io/posts/2025-09-14-llms-agentic.html][What Makes Modern Day LLMs Agentic]] #Agents #ToolCalling #Júlia
+ [[https://huggingface.co/blog/dvilasuero/choosing-best-open-source-ai-models][How to Choose the Best Open Source LLM for Your Project in 2025]] #AISheets #LLMs
+ [[https://www.langtrace.ai/blog/build-a-reliable-summarization-system-using-dspy-and-langtrace][Build a reliable Summarization system using DSPy and Langtrace]] #DSPY #Mirari
+ [[https://psychiatryonline.org/doi/10.1176/appi.ps.20250086][Evaluation of Alignment Between Large Language Models and Expert Clinicians in Suicide Risk Assessment]] #Pablo #Prevenia
+ [[https://thinkingmachines.ai/blog/defeating-nondeterminism-in-llm-inference/][Defeating Nondeterminism in LLM Inference]] #LLMs
+ [[https://www.vanderschaar-lab.com/ai-agents/][AI Agents: Past, Present, and Future ]] #Agents #ChistERA
+ [[https://huggingface.co/blog/mmbert][mmBERT: ModernBERT goes Multilingual]] #Bert #Leo #Multilingual #ChistERA
+ [[https://huggingface.co/blog/embeddinggemma][Welcome EmbeddingGemma, Google's new efficient embedding model]] #Embeddings #Multilingual #ChistERA #Pablo
+ [[https://kargarisaac.medium.com/building-and-optimizing-multi-agent-rag-systems-with-dspy-and-gepa-2b88b5838ce2][Building and Optimizing Multi-Agent RAG Systems with DSPy and GEPA]] #DSPY #Chist-ERA #Mirari
+ [[https://arxiv.org/abs/2507.19457][GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning]] #DSPY #PromptOptimization
+ [[https://www.youtube.com/watch?v=H4o7h6ZbA4o][Ejemplo de DSPy GEPA: reordenador por lista]] #DSPY #AnalisisSentimientos #Pablo
+ [[https://arxiv.org/abs/2506.02153][Small Language Models are the Future of Agentic AI]] #Agents #Mirari #Chist-ERA
+ [[https://github.com/resemble-ai/chatterbox?tab=readme-ov-file][Chatterbox TTS]] #SpeechToText #MultiLingual #Chist-ERA
+ [[https://occiglot.eu/][Occiglot]] #LLM #Júlia #Chistera

** Agosto 2025

+ [[https://www.sciencedirect.com/science/article/pii/S2643651524002103?via%3Dihub][One to All: Toward a Unified Model for Counting Cereal Crop Heads Based on Few-Shot Learning]] #SAM #FewShot #ComputerVision
+ [[https://arxiv.org/abs/2406.06608][The Prompt Report: A Systematic Survey of Prompt Engineering Techniques]] #Prompting #DSPY #PrevenIA #Pablo
+ [[https://www.bmj.com/content/372/bmj.n71][The PRISMA 2020 statement: an updated guideline for reporting systematic reviews]] #SystematicReview #Júlia
+ [[https://arxiv.org/pdf/2401.12178][In-Context Learning for Extreme Multi-Label Classification]] #DSPY #Mirari
+ [[https://arxiv.org/pdf/2508.15882][Beyond Transcription: Mechanistic Interpretability in ASR]] #ASR #Interpretability
+ [[https://arxiv.org/pdf/2505.09970][Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents]] #Júlia
+ [[https://arxiv.org/abs/2408.02865][VisionUnite: A Vision-Language Foundation Model for Ophthalmology Enhanced with Clinical Knowledge]] #optretina
+ [[https://arxiv.org/abs/2311.12983][GAIA: a benchmark for General AI Assistants]] #Júlia #Dataset
+ [[https://huggingface.co/nvidia/canary-1b-v2][🐤 Canary 1B v2: Multitask Speech Transcription and Translation Model]] #mirari #Sara #ASR
+ [[https://onlinelibrary.wiley.com/doi/10.1002/ima.70185][GlaucoDiff: A Framework for Generating Balanced Glaucoma Fundus Images and Improving Diagnostic Performance]] #Elena #Adrián #retina
+ [[https://www.sciencedirect.com/science/article/pii/S0148296321003155][How to conduct a bibliometric analysis: An overview and guidelines]] #bibliometricAnalysis #Júlia 
+ [[https://huggingface.co/blog/trackio][Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face]] #Tracking
+ [[https://arxiv.org/abs/2506.19234][Quantitative Benchmarking of Anomaly Detection Methods in Digital Pathology]] #Bruno #Joaquín #AnomalyDetection #SpectralGeo
+ [[https://research.google/blog/helping-everyone-build-ai-for-healthcare-applications-with-open-foundation-models/][Helping everyone build AI for healthcare applications with open foundation models]] #Bruno #Joaquin
+ [[https://neulab.github.io/CulturalGround/][CulturalGround Grounding Multilingual Multimodal LLMs With Cultural Knowledge]] #chistera #dataset #multimodal
+ [[https://www.dropbox.com/scl/fi/t8d59wupeeb3bdldhbq6o/Beyond-Naive-RAG-Practical-Advanced-Methods.pdf?ajs_uid=720146&rlkey=y0aawyxocpadmq461h752xrg0&e=3&st=i341qxc4&dl=0][Beyond naive RAG]] #rag #pablo #Júlia 
+ [[https://gorilla.cs.berkeley.edu/blogs/13_bfcl_v3_multi_turn.html][🦍 Gorilla: Large Language Model Connected with Massive APIs]] #Júlia #Evaluation #functionc]]alling
+ [[https://www.databricks.com/blog/unpacking-function-calling-eval][Beyond the Leaderboard: Unpacking Function Calling Evaluation]] #Júlia #Evaluation #functioncalling
+ [[https://techcommunity.microsoft.com/blog/azure]]-ai-foundry-blog/evaluating-fine-tuned-models-for-function-calling-beyond-input-output-metrics/4363864][Evaluating Fine-]]Tuned Models for Function-Calling: Beyond Input-Output Metrics]] #Júlia #Evaluation #functioncalling
+ [[https://huggingface.co/blog/welcome-openai-gpt-oss][Welcome GPT OSS, the new open-source model family from OpenAI!]] #Pablo
+ [[https://huggingface.co/blog/aisheets][Introducing AI Sheets: a tool to work with datasets using open AI models!]] #Pablo #Júlia
+ [[https://rua.ua.es/server/api/core/bitstreams/a0f28316-a02f-4335-a765-a162a1364c3f/content][La lecturabilidad de textos escritos en lengua espyearla: revisión crítica de métricas y propuesta de nuevas variables]]] #lecturabilidad #Mirari 

** Julio 2025

+ [[https://arxiv.org/abs/2408.08849][ECG-Chat: A Large ECG-Language Model for Cardiac Disease Diagnosis]] #multimodal
+ [[https://arxiv.org/abs/2507.03152][Expert-level validation of AI-generated medical text with scalable language models]] #Julia #dspy #SyntheticData
+ [[https://boxiyu.github.io/assets/pdf/DSPy_Guardrails.pdf][DSPy Guardrails: Building Safe LLM Applications via Self-Refining Language Model Pipelines]] #dspy #guardrails] #pablo
+ [[https://arxiv.org/pdf/2506.21734][Hierarchical Reasoning Model]] #Reasoning
+ [[https://arxiv.org/pdf/2507.11299][Dr.Copilot: A M]]ulti-Agent Prompt Optimized Assistant for Improving Patient-Doctor Communication in Romanian]] #Chistera #DSPY
+ [[https://arxiv.org/pdf/2507.15245][SPAR: Scholar Paper Retrieval with LLM-based Agents for Enhanced Academic Search]] #Chistera
+ [[https://arxiv.org/pdf/2412.13091][LMUNIT: Fine-grainedEvaluationwithNaturalLanguageUnitTests]]#Júlia #Evaluation
+ [[https://dl.acm.org/doi/10.1145/3726302.3729931][Combining Evidence and Reasoning for Biomedical Fact-Checking]] #Chistera
+ [[https://huggingface.co/learn/cookbook/fine_tuning_vlm_object_detection_grounding][Fine tuning a VLM for Object Detection Grounding using TRL]] #ObjectDetection #Grounding
+ [[https://aclanthology.org/2024.findings-acl.658/][On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey]] #Júlia #SyntheticData
+ [[https://arxiv.org/abs/2209.01975][Selective Annotation Makes Language Models Better Few-Shot Learners]] #ActiveLearning #Joaquin
+ [[https://dl.acm.org/doi/10.1145/3726302.3729882][A New HOPE:Domain-agnostic Automatic Evaluation of Text Chunking]] #Júlia #RAG #Metrics
+ [[https://dl.acm.org/doi/10.1145/3726302.3730221][Limitations of Automatic Relevance Assessments with Large Language Models for Fair and Reliable Retrieval Evaluation]] #Júlia #LLM-as-a-judge
+ [[https://huggingface.co/blog/manu/colqwen-omni-omnimodal-retrieval][Introducing ColQwen-Omni: Retrieve in every modality]] #Sara #MultiModal #RAG
+ [[https://papers.miccai.org/miccai-2024/paper/3154_paper.pdf][FissionFusion: Fast Geometric Generation and Hierarchical Souping for Medical Image Analysis]] #ModelSoups #Joaquin
+ [[https://huggingface.co/blog/ettin][Ettin Suite: SoTA Paired Encoders and Decoders]] #LLMs #Encoder #Decoder
+ [[https://openreview.net/forum?id=j3totqf8xW][Position: Beyond Assistance – Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Care]] #Pablo #Evaluation
+ [[https://arxiv.org/abs/2403.10131v1][RAFT: Adapting Language Model to Domain Specific RAG]] #Pablo #RAG
+ [[https://arxiv.org/abs/2501.11929v1][ALoFTRAG: Automatic Local Fine Tuning for Retrieval Augmented Generation]] #Pablo #RAG
+ [[https://arxiv.org/abs/2505.24478][Optimizing the Interface Between Knowledge Graphs and LLMs for Complex Reasoning]] #GraphRAG #LLMs #Pablo #Júlia
+ [[https://hamel.dev/notes/llm/rag/p2-evals.html][Modern IR Evals For RAG]] #Julia
+ [[https://arxiv.org/abs/2203.05482v3][Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time]] #ModelSoups #Joaquin
+ [[https://huggingface.co/blog/smollm3][SmolLM3: smol, multilingual, long-context reasoner]] #Reasoning #Multilingual
+ [[https://huggingface.co/blog/structured-codeagent][CodeAgents + Structure: A Better Way to Execute Actions]] #CodeAgents
+ [[https://hamel.dev/blog/posts/evals-faq/][Frequently Asked Questions (And Answers) About AI Evals]] #RAG #Júlia
+ [[https://jxnl.co/writing/2025/05/19/there-are-only-6-rag-evals/][There Are Only 6 RAG Evals]] #RAG #Júlia
+ [[https://drive.google.com/file/d/1GVPdwEh48bErTNdhxD0vqxPAifSx1I6Y/view][Agents Companion]] #Agents
+ [[https://docs.google.com/spreadsheets/d/19jzLgRruG9kjUQNKtCg1ZjdD6l6weA6qRXG5zLIAhC8/edit?gid=150872633#gid=150872633][Anthropic's Prompt Engineering Interactive Tutorial]] #Prompting
+ [[https://github.com/unslothai/notebooks/?tab=readme-ov-file][📒 Fine-tuning Notebooks]] #Learning
+ [[https://github.com/NazirNayal8/UEM-likelihood-ratio][A Likelihood Ratio-Based Approach to Segmenting Unknown Objects (IJCV 2025)]] #Segmentation #OOD
+ [[https://www.iic.uam.es/procesamiento-del-lenguaje-natural/llms-como-sintetizadores-de-respuestas/][LLMs como sintetizadores de respuestas]] #Júlia
+ [[https://arxiv.org/abs/2505.21344][The Multilingual Divide and Its Impact on Global AI Safety]] #Multilingual #Chistera

** Junio 2025

+ [[https://github.com/confident-ai/deepeval?tab=readme-ov-file][DeepEval. The LLM Evaluation Framework]] #Júlia #Evaluation
+ [[https://huggingface.co/Intelligent-Internet/II-Medical-8B-1706][II-Medical-8B: Medical Reasoning Model]] #Chistera #Model
+ [[https://med-miriad.github.io/][MIRIAD: Augmenting LLMs with millions of medical query-response pairs]] #Chistera #Dataset
+ [[https://hazyresearch.stanford.edu/blog/2025-05-12-security][Mind the Trust Gap: Fast, Private Local-to-Cloud LLM Chat]] #Security #Privacy
+ [[https://datos.gob.es/es/blog/inteligencia-artificial-sostenible-como-minimizar-el-impacto-ambiental-de-la-ia][Inteligencia artificial sostenible: cómo minimizar el impacto ambiental de la IA]] #CIAIS
+ [[https://huggingface.co/papers/2506.09513][ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning]] #Chistera #Dataset #Medicine
+ [[https://mistral.ai/news/magistral][Stands to reason. Magistral]] #Chistera #Multilingual #Reasoning
+ [[https://arxiv.org/abs/2501.03200][The FACTS Grounding Leaderboard: Benchmarking LLMs’ Ability to Ground Responses to Long-Form Input]] #Júlia #Factuality
+ [[https://riuma.uma.es/xmlui/bitstream/handle/10630/37603/Ana%CC%81lisis%20de%20sentimiento%20del%20espan%CC%83ol%20basado%20en%20corpus%20%282%29.pdf?sequence=6&isAllowed=y][Análisis de sentimiento del espyearl basado en corpus]] #AnalisisSentimientos #MasterNLP
+ [[https://arxiv.org/abs/2505.24478][Optimizing the Interface Between Knowledge Graphs and LLMs for Complex Reasoning]] #GraphRAG #Pablo

** Mayo 2025

+ [[https://www.thelancet.com/journals/landig/article/PIIS2589-7500(25)00040-8/fulltext][Non-invasive biopsy diagnosis of diabetic kidney disease via deep learning applied to retinal images: a population-based study]] #OPTRetina
+ [[https://huggingface.co/blog/diffusers-quantization][Exploring Quantization Backends in Diffusers]] #Quantization
+ [[https://huggingface.co/blog/python-tiny-agents][Tiny Agents in Python: an MCP-powered agent in ~70 lines of code]] #Agents
+ [[https://www.lmms-lab.com/posts/aero_audio/][Aero-1-Audio]] #Audio #ASR #Mirari
+ [[https://huggingface.co/blog/autoround][What is AutoRound?]] #Quantization
+ [[https://www.thelancet.com/journals/landig/article/PIIS2589-7500(25)00042-1/fulltext][FaceAge, a deep learning system to estimate biological age from face photographs to improve prognostication: a model development and validation study]] #Medicine
+ [[https://huggingface.co/blog/vlms-2025][Vision Language Models (Better, Faster, Stronger)]] #VLM
+ [[https://ollama.com/blog/multimodal-models][Ollama's new engine for multimodal models]] #MultiModal
+ [[https://huggingface.co/lightonai/Reason-ModernColBERT][Reason-ModernColBERT]] #Chistera #Retrieval
+ [[https://developers.google.com/health-ai-developer-foundations/medgemma/model-card][MedGemma]] #Chistera
+ [[https://github.com/weaviate/recipes/blob/main/weaviate-features/multi-vector/reason_moderncolbert.ipynb][Multi-vector embeddings with Reasoning-ModernColBERT]] #Retrieval #Reasoning #RAG #Chistera
+ [[https://huggingface.co/spaces/google/rad_explain][Medgemma demo]] #CienciaEnClaro 
+ [[https://huggingface.co/collections/google/medgemma-release-680aade845f90bec6a3f60c4][MedGemma]] #Chistera #Leo 
+ [[https://github.com/guardrails-ai/guardrails?tab=readme-ov-file][Guardrails AI]] #GuardRails #Pablo
+ [[https://huggingface.co/docs/transformers/model_doc/grounding-dino][Grounding DINO]] #instancesegmentation #Joaquín #ObjectDetection
+ [[https://huggingface.co/blog/whitecircle-ai/circleguardbench][CircleGuardBench: New Standard for Evaluating AI Moderation Models]] #Guards #prevenia 
+ [[https://shap.readthedocs.io/en/latest/text_examples.html#sentiment-analysis][Explicabilidad Análisis Sentimiento]] #SentimentAnalysis #MasterNLP #Explicabilidad
+ [[https://www.biorxiv.org/content/10.1101/2025.04.28.651001v1.full.pdf][Cellpose-SAM: superhuman generalization for cellular segmentation]] #CellSegmentation #Arrate
+ [[https://cacm.acm.org/research/envisioning-recommendations-on-an-llm-based-agent-platform/#F3][Envisioning Recommendations on an LLM-Based Agent Platform]] #Agents #ChistERA #RecommendationSystems
+ [[https://ai.meta.com/blog/meta-fair-updates-perception-localization-reasoning/?utm_source=twitter&utm_medium=organic%20social&utm_content=video&utm_campaign=fair][Advancing AI systems through progress in perception, localization, and reasoning]] #Agents #Imaging
+ [[https://colab.research.google.com/github/stanford-futuredata/ColBERT/blob/main/docs/intro2new.ipynb][ColBERTv2: Indexing & Search Notebook]] #ColBERT #PrevenIA
+ [[https://huggingface.co/jinaai/jina-colbert-v2][JinaColBERT V2: A General-Purpose Multilingual Late Interaction Retriever]] #ColBERT #PrevenIA
+ [[https://www.lighton.ai/lighton-blogs/pylate-flexible-training-and-retrieval-for-late-interaction-models][PyLate: Flexible Training and Retrieval for ColBERT Models]] #ColBERT #PrevenIA
+ [[https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_finetune_on_a_custom_dataset.ipynb][Fine-tuning D-Fine on a custom dataset]] #ObjectDetection #Master 
+ [[https://huggingface.co/blog/sasha/reduce-reuse-recycle][Reduce, Reuse, Recycle: Why Open Source is a Win for Sustainability]] #CIAIS #Felix
+ [[https://datos.gob.es/es/blog/como-elegir-el-grafico-correcto-para-visualizar-datos-abiertos][Cómo elegir el gráfico correcto para visualizar datos abiertos]] #Visualización
+ [[https://huggingface.co/collections/Unbabel/xcomet-659eca973b3be2ae4ac023bb][xCOMET]] #Chist-ERA
+ [[https://huggingface.co/collections/Unbabel/tower-659eaedfe36e6dd29eb1805c][Tower]] #Chist-ERA
+ [[https://huggingface.co/blog/eurollm-team/eurollm-9b][EuroLLM-9B]] #Chist-ERA

** Abril 2025

+ [[https://huggingface.co/blog/gradio-mcp][How to Build an MCP Server in 5 Lines of Python]] #MCP 
+ [[https://huggingface.co/blog/llama-guard-4][Welcoming Llama Guard 4 on Hugging Face Hub]] #Safety #PrevenIA
+ [[https://www.ncbi.nlm.nih.gov/books/NBK602381/][Chatbots in Health Care: Connecting Patients to Information]] #PrevenIA #ChistERA
+ [[https://arxiv.org/abs/2504.11833][Could Thinking Multilingually Empower LLM Reasoning?]] #Multilingual #Reasoning #Chistera
+ [[https://huggingface.co/blog/Kseniase/mcp][🦸🏻#14: What Is MCP, and Why Is Everyone – Suddenly!– Talking About It?]] #MCP #Agents #Tools #Chistera
+ [[https://arxiv.org/abs/2310.13960][Linguistically Motivated Sign Language Segmentation]] #LSEAvatar 
+ [[https://arxiv.org/abs/2504.10822][IlluSign: Illustrating Sign Language Videos by Leveraging the Attention Mechanism]]
+ [[https://github.com/sign-language-processing][Sign Language Processing]] #LSEAvatar 
+ [[https://link.springer.com/article/10.1007/s00146-025-02340-8][Bullshit universities: the future of automated education]] #CIAIS
+ [[https://arxiv.org/abs/2504.15205][Support Evaluation for the TREC 2024 RAG Track: Comparing Human versus LLM Judges]]  #Júlia #RAG
+ [[https://arxiv.org/abs/2411.08275][A Large-Scale Study of Relevance Assessments with Large Language Models: An Initial Look]] #Júlia #RAG
+ [[https://arxiv.org/abs/2411.09607][Initial Nugget Evaluation Results for the TREC 2024 RAG Track with the AutoNuggetizer Framework]] #Júlia #RAG
+ [[https://huggingface.co/papers/2504.11544][NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes]] #GraphRAG #Júlia #Multihop
+ [[https://huggingface.co/papers/2504.10479?utm_source=digest-papers&utm_medium=email&utm_campaign=2025-04-15][InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models]] #MultiModal #MLLM
+ [[https://magazine.sebastianraschka.com/p/the-state-of-llm-reasoning-model-training?utm_campaign=post][The State of Reinforcement Learning for LLM Reasoning]] #ReinforcementLearning
+ [[https://huggingface.co/blog/helmet][Introducing HELMET: Holistically Evaluating Long-context Language Models]] #Evaluation #LongContext
+ [[https://mirage-bench.github.io/][MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems]] #Júlia #RAG #Evaluation 
+ [[https://developers.googleblog.com/en/agent-development-kit-easy-to-build-multi-agent-applications/?utm_source=ai-report.kdnuggets.com&utm_medium=newsletter&utm_campaign=building-ai-agents-just-got-easier][Agent Development Kit: Making it easy to build multi-agent applications]] #Agents #Chistera
+ [[https://huggingface.co/papers/2504.05305?utm_source=digest-papers&utm_medium=email&utm_campaign=2025-04-08][URECA: Unique Region Caption Anything]] #ImageCaptioning
+ [[https://huggingface.co/papers/2504.05298][One-Minute Video Generation with Test-Time Training]] #VideoGeneration
+ [[https://huggingface.co/papers/2504.05299?utm_source=digest-papers&utm_medium=email&utm_campaign=2025-04-08][SmolVLM: Redefining small and efficient multimodal models]] #VLM #Chistera
+ [[https://contextual.ai/blog/is-rag-dead-yet/][RAG is dead, long live RAG!]] #RAG
+ [[https://www.pikaramagazine.com/2025/04/cuando-interesan-nuestros-cuerpos-a-la-ia/][¿Cuándo interesan nuestros cuerpos a la IA?]] #CIAIS
+ [[https://arxiv.org/abs/2503.18813][Defeating Prompt Injections by Design]] #Security #LLMs
+ [[https://isshikihugh.github.io/HSMR/][Reconstructing Humans with a Biomechanically Accurate Skeleton]] #LSEAvatar
+ [[https://humansensinglab.github.io/Hamba/][Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba]] #LSEAvatar
+ [[https://arxiv.org/abs/2402.15350][Farsight: Fostering Responsible AI Awareness During AI Application Prototyping]] #CIAIS #Safeness
+ [[https://arxiv.org/abs/2502.18600][Chain of Draft: Thinking Faster by Writing Less]] #Prompting #LLMs

** Marzo 2025

+ [[https://www.polibits.cidetec.ipn.mx/ojs/index.php/CyS/article/view/5538][Automatic Translation of Sentences to Mexican Sign Language: Rule-based Machine Translation and Animation Synthesis in Avatar]] #LSEAvatar
+ [[https://huggingface.co/blog/train-reranker][Training and Finetuning Reranker Models with Sentence Transformers v4]] #Pablo #PrevenIA
+ [[https://www.anthropic.com/research/tracing-thoughts-language-model][Tracing the thoughts of a large language model]] #Interpretability
+ [[https://static.makehumancommunity.org/makehuman.html][MAKEHUMAN]] #Blender #Avatar #LenguaSignos
+ [[https://huggingface.co/coqui/XTTS-v2][coqui/XTTS-v2]] #TextToSpeech #Chistera
+ [[https://diamantai.substack.com/p/building-an-ai-agent-with-memory?r=336pe4&utm_campaign=post&utm_medium=web&triedRedirect=true][Building an AI Agent with Memory and Adaptability]] #Agents #Memory
+ [[https://huggingface.co/papers/2503.00865][Babel: Open Multilingual Large Language Models Serving Over 90% of Global Speakers]] #MultiLingual #Chistera
+ [[https://huggingface.co/blog/llm-inference-on-edge][LLM Inference on Edge: A Fun and Easy Guide to run LLMs via React Native on your Phone!]] #Inference  #Phones
+ [[https://huggingface.co/blog/jfrog][Hugging Face and JFrog partner to make AI Security more transparent]] #ModelSafety
+ [[https://huggingface.co/blog/mlabonne/abliteration][Uncensor any LLM with abliteration]] #Jailbreaking
+ [[https://arxiv.org/abs/2503.10970][TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools]] #Agents #CHISTERA
+ [[https://www.sciencedirect.com/science/article/pii/S2352340925001696#sec0005][TELEIA: A Spanish language dataset for evaluating artificial intelligence models]] #Dataset #Sara #Manu #Mirari
+ [[https://huggingface.co/blog/xet-on-the-hub][Xet is on the Hub]] #Chistera #DataStorage
+ [[https://huggingface.co/datasets/praiselab-picuslab/MMMED][MMMED: Multilingual Medical Visual Question Answering Dataset]] #Dataset #Chistera
+ [[https://huggingface.co/datasets/lewoniewski/wikipedia_quality_wikirank][WikiRank]] #Dataset
+ [[https://karpathy.bearblog.dev/digital-hygiene/][Digital hygiene]]
+ [[https://hackernoon.com/ai-chatbots-are-getting-too-good-at-making-you-say-yes][AI Chatbots Are Getting Too Good at Making You Say ‘Yes’]] #CIAIS #EmpathicChatbots
+ [[https://huggingface.co/blog/EuroBERT/release][Introducing EuroBERT: A High-Performance Multilingual Encoder Model]] #ChistERA #Embedding
+ [[https://huggingface.co/blog/adaamko/lettucedetect][LettuceDetect: A Hallucination Detection Framework for RAG Applications]] #Hallucinations #RAG
+ [[https://jamanetwork.com/journals/jama/fullarticle/2831048][Researcher Proposes New Framework for Language Equity in Health Technology]] #Chistera
+ [[https://www.cambridge.org/core/journals/the-british-journal-of-psychiatry/article/detection-of-suicidality-from-medical-text-using-privacypreserving-large-language-models/75E6B08AECDF68443C2594F421805FD9?utm_campaign=shareaholic&utm_medium=email_this&utm_source=email][Detection of suicidality from medical text using privacy-preserving large language models]] #Pablo
+ [[https://huggingface.co/blog/aya-vision][A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodality]] #Multilingual #MultiModal #Chistera
+ [[https://www.scienceopen.com/document?vid=353ffdd6-2872-4fc5-9525-5b5fd6c36cec][Applications of Large Language Models in the Field of Suicide Prevention: Scoping Review]] #Pablo #Review
+ [[https://www.tanishq.ai/blog/posts/llm-medical-evals][LLMs in medicine: evaluations, advances, and the future]] #LLMs #Medicine
+ [[https://opentelemetry.io/docs/what-is-opentelemetry/][OpenTelemetry]] #ChistERA

** Febrero 2025

+ [[https://github.com/octotools/octotools][OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning]] #Agents #Chistera
+ [[https://huggingface.co/blog/siglip2][SigLIP 2: A better multilingual vision language encoder]] #VisualEncoder
+ [[https://blogs.nvidia.com/blog/ai-sign-language/][It’s a Sign: AI Platform for Teaching American Sign Language Aims to Bridge Communication Gaps]] #LenguaSignos
+ [[https://link.springer.com/article/10.1007/s00417-023-06101-5][Insights into artificial intelligence in myopia management: from a data perspective]] #Miopia #Elena
+ [[https://arxiv.org/abs/2501.19393][s1: Simple test-time scaling]] #TestTimeScaling
+ [[https://arxiv.org/abs/2501.18099][Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge]] #LLMasaJudge
+ [[https://langchain-ai.github.io/langgraph/tutorials/workflows/][Workflows and Agents]] #Agents #Chistera
+ [[https://huggingface.co/papers/2502.02737][SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model]] #SmallLLM
+ [[https://huggingface.co/blog/dabstep][DABStep: Data Agent Benchmark for Multi-step Reasoning]] #Agents #Reasoning
+ [[https://magazine.sebastianraschka.com/p/understanding-reasoning-llms?utm_campaign=email-half-post&r=f2umh&utm_source=substack&utm_medium=email][Understanding Reasoning LLMs]] #Reasoning
+ [[https://arxiv.org/abs/2502.00418][Parameter Efficient Fine-Tuning of Segment Anything Model]] #PEFT #SAM #Miopia
+ [[https://huggingface.co/posts/Kseniase/113319295427497][8 New Types of RAG]] #RAG #Pablo
+ [[https://x.com/reach_vb/status/1889015111890997479][Zonos Text to Speech]] #TextToSpeech
+ [[https://github.com/facebookresearch/mils?tab=readme-ov-file][LLMs can see and hear without any training]] #MultiModal #Reasoning
+ [[https://huggingface.co/papers/2502.05163][DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails]] #GuardRails #MultiLingual #Pablo
+ [[https://x.com/NielsRogge/status/1889362871995474212][RT-DETRv2]] #ObjectDetection
+ [[https://huggingface.co/docs/transformers/main/en/model_doc/depth_pro][Depth Pro]] #LSEAvatar #DepthEstimation
+ [[https://github.com/qubvel/rt-pose][RT-Pose]] #LSEAvatar #Pose 
+ [[https://github.com/damo-cv/RealisDance][RealisDance: Equip controllable character animation with realistic hands]] #LSEAvatar
+ [[https://antgroup.github.io/ai/echomimic_v2/][EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation]] #LSEAvatar
+ [[https://huggingface.co/blog/billion-classifications][1 Billion Classifications]] #CostEstimation
+ [[https://huggingface.co/blog/vid_ds_scripts][Build awesome datasets for video generation]] #VideoDataset
+ [[https://newsletter.maartengrootendorst.com/p/a-visual-guide-to-reasoning-llms][A Visual Guide to Reasoning LLMs]] #Reasoning #DeepSeek
+ [[https://unfoldai.com/reasoning-in-a-non-english-language/][Reasoning model in a non-English language using GRPO trainer (TRL) and Unsloth]] #GRPO #Reasoning #DeepSeek
+ [[https://huggingface.co/blog/open-deep-research][Open-source DeepResearch – Freeing our search agents]] #Agents
+ [[https://huggingface.co/papers/2501.18492][GuardReasoner: Towards Reasoning-based LLM Safeguards]] #GuardRails
+ [[https://huggingface.co/blog/ai-art-newsletter-jan-25][The AI tools for Art Newsletter]] #ImageGeneration #VideoGeneration #AudioGeneration
+ [[http://mt-class.org/jhu/syllabus.html][Machine Translation]] #TraduccionAutomatica #Clases
+ [[https://arxiv.org/abs/2501.18362][MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding]] #Chistera #Dataset
+ [[https://www.iic.uam.es/noticias/rigochat-v2-adaptando-llms-al-espanol-con-fines-practicos-y-recursos-limitados/][RigoChat-v2: adaptando LLMs al espyearl con fines prácticos y recursos limitados]] #LLMs #RigoChat
+ [[https://huggingface.co/blog/open-r1/update-1][Open-R1: Update #1]] #DeepSeek
+ [[https://arxiv.org/abs/2409.06790][Translating Step-by-Step: Decomposing the Translation Process for Improved Translation Quality of Long-Form Texts]] #TraduccionAutomatica #Chistera


** Enero 2025

+ [[https://arxiv.org/abs/2501.15654][People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text]] #AIDetection
+ [[https://github.com/roboflow/notebooks][Roboflow notebooks]] #Teaching #ComputerVision
+ [[https://danielvanstrien.xyz/posts/2025/deepseek/distil-deepseek-modernbert.html][Distiling DeepSeek reasoning to ModernBERT classifiers]] #SyntheticData
+ [[https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1][The Illustrated DeepSeek-R1]] #DeepSeek
+ [[https://huggingface.co/blog/open-r1][Open-R1: a fully open reproduction of DeepSeek-R1]] #DeepSeek #ReinforcementLearning
+ [[https://huggingface.co/blog/inference-providers][Welcome to Inference Providers on the Hub 🔥]] #Inference
+ [[https://arxiv.org/abs/2407.08223][Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting]] #RAG #Pablo #Agents
+ [[https://huggingface.co/blog/video_gen][State of open video generation models in Diffusers]] #VideoGeneration
+ [[https://colab.research.google.com/drive/1Eq9trtE2FFG9KKXwvHBvUAtMJkhxVBtV#scrollTo=dd2LpXrvgYGB][Graph RAG with Unstructured and AstraDB]] #GraphRAG #Pablo
+ [[https://huggingface.co/papers/2501.03895?utm_source=digest-papers&utm_medium=email&utm_campaign=2025-01-08][LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token]] #VLM
+ [[https://www.nature.com/articles/s44401-024-00004-1][Retrieval-augmented generation for generative artificial intelligence in health care]] #RAG #Medicine #Pablo
+ [[https://huggingface.co/papers/2501.12948][DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning]] #ReinforcementLearning #Reasoning
+ [[https://huggingface.co/papers/2501.04001][Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos]] #Videos 
+ [[https://cohere.com/blog/towards-fair-and-comprehensive-multilingual-and-multicultural-llm-benchmarking][Towards fair and comprehensive multilingual and multicultural LLM benchmarking]] #LLMs #Evaluation
+ [[https://huggingface.co/blog/asoria/datadreamer-datasets][Exploring Synthetic Data Generation with DataDreamer]] #SyntheticData
+ [[https://www.dataprovenance.org/Multimodal_Data_Provenance.pdf][BRIDGING THE DATA PROVENANCE GAP ACROSS TEXT, SPEECH, AND VIDEO]] #DataProvenance #ProyectoNacional2024
+ [[https://blogs.upm.es/iayaccesibilidadcognitiva/produccion-cientifica/publicaciones-en-revista/][Inteligencia Artificial y Accesibilidad Cognitiva]] #LecturaFacil #Mirari #PlenaInclusion
+ [[https://huggingface.co/blog/smolervlm][SmolVLM Grows Smaller – Introducing the 250M & 500M Models!]] #ProyectoIA #VLM
+ [[https://www.sciencedirect.com/science/article/pii/S1361841524001269][A comprehensive survey on deep active learning in medical image analysis]] #ActiveLearning #Joaquin #Adrian
+ [[https://www.sciencedirect.com/science/article/pii/S0952197623009892#sec3][Density-based one-shot active learning for image segmentation]] #ActiveLearning #Joaquin #Adrian
+ [[https://arxiv.org/pdf/2501.05441][The GAN is dead; long live the GAN! A Modern Baseline GAN]] #GANs
+ [[https://jamanetwork.com/journals/jama/fullarticle/2814246?utm_source=silverchair&utm_campaign=jama_network&utm_content=article_alert-jama_ai&utm_medium=email&adv=][AI’s Threat to the Medical Profession]] #CIAIS #Medicine
+ [[https://sakana.ai/transformer-squared/][Transformer²: Self-Adaptive LLMs]] #LLMs
+ [[https://github.com/NirDiamant/Controllable-RAG-Agent][Sophisticated Controllable Agent for Complex RAG Tasks 🧠📚]] #RAG #Pablo #Agents
+ [[https://github.com/bRAGAI/bRAG-langchain][Retrieval-Augmented Generation (RAG) Project]] #RAG #Pablo
+ [[https://huggingface.co/learn/cookbook/rag_with_knowledge_graphs_neo4j][Enhancing RAG Reasoning with Knowledge Graphs]] #RAG #Graphs #Pablo
+ [[https://huggingface.co/learn/cookbook/search_and_learn][Scaling Test-Time Compute for Longer Thinking in LLMs]] #TestTimeCompute #LLMs
+ [[https://www.sciencedirect.com/science/article/pii/S0952197624021547][An effective skeleton-based approach for multilingual sign language recognition]] #LSEAvatar
+ [[https://huggingface.co/blog/leaderboard-emissions-analysis][CO₂ Emissions and Models Performance: Insights from the Open LLM Leaderboard]] #CIAIS #Felix #CO2
+ [[https://huggingface.co/blog/vdr-2b-multilingual][Visual Document Retrieval Goes Multilingual]] #DocumentRetrieval #SyntheticData
+ [[https://www.synthlabs.ai/research/meta-chain-of-thought][Meta Chain-of-Thought: Unlocking System 2 Reasoning in LLMs]] #LLMs #CoT
+ [[https://huggingface.co/blog/static-embeddings][Train 400x faster Static Embedding Models with Sentence Transformers]] #Embeddings
+ [[https://huggingface.co/blog/timm-transformers][Timm ❤️ Transformers: Use any timm model with transformers]] [[https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/image_classification.ipynb][Image Classification HuggingFace]] #ImageClassification
+ [[https://huggingface.co/blog/ethics-soc-7][AI Agents Are Here. What Now?]] #Agents #Mirari #ProyectoIA
+ [[https://nvidianews.nvidia.com/news/nvidia-puts-grace-blackwell-on-every-desk-and-at-every-ai-developers-fingertips][NVIDIA Puts Grace Blackwell on Every Desk and at Every AI Developer’s Fingertips]] #GPUs #ProyectoNacional
+ [[https://x.com/NirDiamantAI/status/1875964427922702731][Controllable RAG Agent]] #RAG #Agents #Pablo [[https://github.com/NirDiamant/Controllable-RAG-Agent][GitHub]]
+ [[https://github.com/virattt/ai-hedge-fund][AI Hedge Fund]] #Agents #JesusVillota
+ [[https://towardsdatascience.com/multi-agentic-rag-with-hugging-face-code-agents-005822122930][Multi-Agentic RAG with Hugging Face Code Agents]] #Agents #Mirari #ProyectoIA
+ [[https://arxiv.org/abs/2501.04001][Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos]] #MLLM
+ [[https://huyenchip.com//2025/01/07/agents.html][Agents]] #ProyectoNacional #Agents 
+ [[https://aiguide.substack.com/p/did-openai-just-solve-abstract-reasoning][Did OpenAI Just Solve Abstract Reasoning?]] #AbstractReasoning #OpenAI
+ [[https://www.gradio.app/guides/agents-and-tool-usage#building-with-visibly-thinking-llms][Building a UI for an LLM Agent]] #ProyectoNacional #Agents #Interfaz
+ [[https://huggingface.co/papers/2501.01149][A3: Android Agent Arena for Mobile GUI Agents]] #ProyectoNacional #Agents
+ [[https://github.com/tonywu71/colpali-cookbooks/blob/main/examples/use_transformers_native_colpali.ipynb][Use the 🤗 transformers-native implementation of ColPali]] #VisualQuestionAnswering #VisualRetrieval
+ [[https://arxiv.org/abs/2311.07397][AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation]] #Hallucinations #MultiModal
+ [[https://github.com/huggingface/smol-course/tree/main][a smol course]] #Course #HuggingFace #LanguageModels
+ [[https://github.com/huggingface/smol-course/blob/main/6_synthetic_datasets/instruction_datasets.md][Generating Instruction Datasets]] #SyntheticData
+ [[https://www.madrimasd.org/blogs/matematicas/2024/12/30/150806][Historias de la IA: los autómatas]] #Automatas
+ [[https://medium.com/@elisowski/ai-agents-vs-agentic-ai-whats-the-difference-and-why-does-it-matter-03159ee8c2b4][AI Agents vs Agentic AI: What’s the Difference and Why Does It Matter?]] #Agents #ProyectoNacional2024
+ [[https://huggingface.co/blog/smolagents][Introducing smolagents, a simple library to build agents]] #Agents #ProyectoNacional2024

** Diciembre 2024

+ [[https://huggingface.co/learn/cookbook/fine_tuning_vlm_dpo_smolvlm_instruct][Fine-tuning SmolVLM using direct preference optimization (DPO) with TRL on a consumer GPU]] #VLMs #Finetuning
+ [[https://huggingface.co/blog/vlms][Vision Language Models Explained]] #VLM
+ [[https://arxiv.org/abs/2309.07864][The Rise and Potential of Large Language Model Based Agents: A Survey]] #Agents #ProyectoNacional2024
+ [[https://arxiv.org/abs/2408.04650][Building Trust in Mental Health Chatbots: Safety Metrics and LLM-Based Evaluation Tools]] #Pablo #PrevenIA
+ [[https://arxiv.org/abs/2412.07769][BiMediX2: Bio-Medical EXpert LMM for Diverse Medical Modalities]] #MedicalLLM #ProyectoIA
+ [[https://huggingface.co/blog/dpo_vlm][Preference Optimization for Vision Language Models with TRL]] #VLM #Quantization
+ [[https://realpython.com/podcasts/rpp/232/][Episode 232: Exploring Modern Sentiment Analysis Approaches in Python]] #SentimentAnalysis #MasterNLP
+ [[https://www.thelancet.com/journals/landig/article/PIIS2589-7500(24)00224-3/fulltext][Tackling algorithmic bias and promoting transparency in health datasets: the STANDING Together consensus recommendations]] #MedicalDatasets #Provenance
+ [[https://huggingface.co/blog/merve/quantization][Introduction to Quantization cooked in 🤗 with 💗🧑‍🍳]] #Quantization
+ [[https://supermedintel.github.io/Medical-SAM2/][Medical SAM 2: Segment medical images as video via Segment Anything Model 2]] #SemanticSegmentation
+ [[https://nexa.ai/blogs/omniaudio-2.6b][OmniAudio-2.6B: World's Fastest Audio Language Model for Edge Deployment]] #AudioLanguageModel
+ [[https://huggingface.co/blog/bamba][Bamba: Inference-Efficient Hybrid Mamba2 Model 🐍]] #Mamba
+ [[https://huggingface.co/blog/big-bench-audio-release][Evaluating Audio Reasoning with Big Bench Audio]] #Audio
+ [[https://huggingface.co/blog/train_memory][Visualize and understand GPU memory in PyTorch]] #GPU #Master
+ [[https://huggingface.co/papers/2412.15484][Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage]] #ImageCaptioning #Agents
+ [[https://huggingface.co/spaces/HuggingFaceH4/blogpost-scaling-test-time-compute][Scaling test-time compute with open models]] #TestTimeCompute
+ [[https://huggingface.co/blog/modernbert][Finally, a Replacement for BERT]] #ModernBERT #Encoder
+ [[https://huggingface.co/blog/logits-processor-zoo][Controlling Language Model Generation with NVIDIA's LogitsProcessorZoo]] #LLMs #Generation
+ [[https://www.philschmid.de/fine-tune-llms-in-2025][How to fine-tune open LLMs in 2025 with Hugging Face]] #LLMs #FineTuning
+ [[https://carlo.ai/posts/fastcore-quantum][Fastcore Transform x QuantumFastcore Transform x Quantum]] #Cuantica
+ [[https://queue.acm.org/detail.cfm?id=3704442][The State of Digital Accessibility]] #Accesibility #Mirari
+ [[https://deepmind.google/discover/blog/facts-grounding-a-new-benchmark-for-evaluating-the-factuality-of-large-language-models/][FACTS Grounding: A new benchmark for evaluating the factuality of large language models]] #Factuality
+ [[https://huggingface.co/learn/cookbook/agent_rag][Agentic RAG: turbocharge your RAG with query reformulation and self-query! 🚀]] #RAG #Agents #ProyectoIA
+ [[https://huggingface.co/learn/cookbook/multimodal_rag_using_document_retrieval_and_reranker_and_vlms][Multimodal RAG with ColQwen2, Reranker, and Quantized VLMs on Consumer GPUs]] #VisualLanguageModels #RAG
+ [[https://link.springer.com/article/10.1007/s00521-024-10776-0][A real-time platform for Spanish Sign Language interpretation]] #LenguaSignos #Manu #Mirari
+ [[https://blog.roboflow.com/fine-tune-paligemma-2/][How to Fine-tune PaliGemma 2]] #VLM #LORA #FineTuning
+ [[https://huggingface.co/blog/image-preferences][Open Preference Dataset for Text-to-Image Generation by the 🤗 Community]] #ImageDataset #ImageGeneration
+ [[https://blog.google/technology/google-deepmind/google-gemini-ai-update-december-2024/][Introducing Gemini 2.0: our new AI model for the agentic era]] #Agents
+ [[https://bair.berkeley.edu/blog/2024/02/18/compound-ai-systems/][The Shift from Models to Compound AI Systems]]  #Nacional2024 #Agents
+ [[https://huggingface.co/blog/paligemma2][Welcome PaliGemma 2 – New vision language models by Google]] #VisualLanguageModels
+ [[https://ollama.com/blog/structured-outputs][Structured outputs]] #Ollama #JSON
+ [[https://github.com/yformer/EfficientTAM?tab=readme-ov-file][Efficient Track Anything Model]] #Tracking #Maria
+ [[https://huggingface.co/blog/cfm-case-study][Investing in Performance: Fine-tune small models with LLM insights - a CFM case study]] #NER #Annotation
+ [[https://huggingface.co/blog/leaderboard-3c3h-aragen][Rethinking LLM Evaluation with 3C3H: AraGen Benchmark and Leaderboard]] #LLMs #Evaluation #Judges
+ [[https://arxiv.org/pdf/2405.12971][BiomedParse: a biomedical foundation model for image parsing of everything everywhere all at once]] #SemanticSegmentation #ImageParsing
+ [[https://www.nature.com/articles/s41746-024-01344-w][The path forward for large language models in medicine is open]] #LLMs #ProyectoNacional2024

** Noviembre 2024

+ [[https://haystack.deepset.ai/blog/swarm-of-agents][Create a Swarm of Agents]] #Agents
+ [[https://aclanthology.org/2024.tsar-1.7.pdf][Society of Medical Simplifiers]] #Agents #TextSimplification #Leo
+ [[https://huggingface.co/blog/smolvlm][SmolVLM - small yet mighty Vision Language Model]] #VisualLanguageModel #ProyectoIA
+ [[https://microsoft.github.io/presidio/][Presidio: Data Protection and De-identification SDK]]  #Anonimización #Mirari #ProyectoSara
+ [[https://www.kaggle.com/code/markishere/day-3-building-an-agent-with-langgraph/][Day 3 - Building an agent with LangGraph]] #Agents #ProyectoIA
+ [[https://www.kaggle.com/whitepaper-agents][Agents]] #Agents #ProyectoIA
+ [[https://learnopencv.com/lightrag/][LightRAG: Simple and Fast Retrieval-Augmented Generation for Legal Doc Analysis]] #GraphLLM #Retrieval #RAG
+ [[https://developers.googleblog.com/es/introducing-mediapipe-solutions-for-on-device-machine-learning/][Presentamos las soluciones de MediaPipe para el aprendizaje automático integrado en el dispositivo]] #MediaPipe #LSEAvatar
+ [[https://ollama.com/blog/llama3.2-vision][Llama 3.2 Vision]] #Ollama #LVM #ProyectoIA
+ [[https://magazine.sebastianraschka.com/p/understanding-multimodal-llms][Understanding Multimodal LLMs]] #MultiModalLLM #ProyectoIA
+ [[https://vectorize.io/multimodal-rag-patterns/][Multimodal RAG Patterns Every AI Developer Should Know]] #MultiModal #RAG #ProyectoIA
+ [[https://accedacris.ulpgc.es/handle/10553/134597][Lectura Fácil: Procesos y entornos de una nueva modalidad de traducción]] #LecturaFacil #Mirari #PlenaInclusion
+ [[https://vectorize.io/how-i-finally-got-agentic-rag-to-work-right/][How I finally got agentic RAG to work right]] #Agents #RAG #ProyectoIA
+ [[https://weaviate.io/blog/what-is-agentic-rag][What is Agentic RAG]] #Agents #RAG #ProyectoIA
+ [[https://medask.tech/blogs/introducing-symptomcheck-bench/][Introducing SymptomCheck Bench]] #Evaluation #Agent
+ [[https://arxiv.org/abs/2305.01275][Segment Anything is A Good Pseudo-label Generator for Weakly Supervised Semantic Segmentation]] #SAM #SemiSupervised #Adrian
+ [[https://arxiv.org/abs/2305.05803][Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentation]] #SAM #SemiSupervised #Adrian

** Octubre 2024

+ [[https://unstructured.io/blog/rag-vs-long-context-models-do-we-still-need-rag][RAG vs. Long-Context Models. Do we still need RAG?]] #RAG
+ [[https://hamel.dev/blog/posts/llm-judge/][Creating a LLM-as-a-Judge That Drives Business Results]] #LLMJudge #Evaluation #Pablo
+ [[https://github.com/argilla-io/distilabel][distilabel: Synthesize data for AI and add feedback on the fly!]] #DataSynthesis #Pablo
+ [[https://huggingface.co/blog/universal_assisted_generation][Universal Assisted Generation: Faster Decoding with Any Assistant Model]] #LLMs #Decoding
+ [[https://huggingface.co/blog/mlabonne/decoding-strategies][Decoding Strategies in Large Language Models]] #LLMs #Decoding
+ [[https://huggingface.co/blog/digital-green-llm-judge][Expert Support case study: Bolstering a RAG app with LLM-as-a-Judge]] #Evaluation #LLMJudge #Pablo
+ [[https://arxiv.org/abs/2410.05993][Aria: An Open Multimodal Native Mixture-of-Experts Model]] #MultiModal #ProyectoIA
+ [[https://stable-diffusion-art.com/animatediff-morphing-transition-video-comfyui/][AnimateDiff morphing transition video (ComfyUI)]] #Morphing
+ [[https://arxiv.org/abs/2410.13458][MedINST: Meta Dataset of Biomedical Instructions]] #MedicalLLM #ProyectoIA
+ [[https://ollama.com/blog/tool-support][Ollama Tool support]] #Tools #Agents
+ [[https://arxiv.org/abs/2410.02707][LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations]] #Hallucinations
+ [[https://arxiv.org/abs/2410.07514][O1O: Grouping of Known Classes to Identify Unknown Objects as Odd-One-Out]] #ObjectDetection #UnknownObjects #IterativeLearning
+ [[https://huggingface.co/blog/cinepile2][CinePile 2.0 - making stronger datasets with adversarial refinement]] #VideoQA
+ [[https://huggingface.co/blog/synthid-text][Introducing SynthID Text]] #Watermarking #FakeDetection
+ [[https://huggingface.co/learn/cookbook/agents][Agents Recipes]] #Agents #ProyectoIA
+ [[https://github.com/computationalstylistics/stylo][stylo: R package for stylometric analyses]] #stylometric #Mapi
+ [[https://huggingface.co/learn/cookbook/multimodal_rag_using_document_retrieval_and_vlms][Multimodal Retrieval-Augmented Generation (RAG) with Document Retrieval (ColPali) and Vision Language Models (VLMs)]] #MultiModalRAG #VLMs 
+ [[https://huggingface.co/HiTZ/EriBERTa-base][EriBERTa A Bilingual Pre-Trained Language Model for Clinical Natural Language Processing]] #MedicalLLM #ProyectoIA
+ [[https://huggingface.co/blog/abhinand/medembed-finetuned-embedding-models-for-medical-ir][MedEmbed: Fine-Tuned Embedding Models for Medical / Clinical IR]] #Embedding #MedicalData #SyntheticData
+ [[https://huggingface.co/blog/sdiazlor/custom-text-classifier-ai-human-feedback][How to build a custom text classifier without days of human labeling]] #TextClassification #DataLabelling #MasterNLP
+ [[https://www.answer.ai/posts/2024-10-15-how-to-synthesize-data.html][How To T̶r̶a̶i̶n̶ Synthesize Your D̶r̶a̶g̶o̶n̶ Data]] #SyntheticData #Mirari #PlenaInclusion
+ [[https://aclanthology.org/2024.findings-acl.198.pdf][Red Teaming Visual Language Models]] #RedTeaming #Pablo #VLM 
+ [[https://github.com/huggingface/evaluation-guidebook][LLM Evaluation Guidebook]] #LLMEvaluation #Pablo
+ [[https://arxiv.org/abs/2409.02897][LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA]] #LongContext #RAG [[https://x.com/rasbt/status/1845468766118850862][twitter]]
+ [[https://homebrew.ltd/blog/llama-learns-to-talk][🍓 Ichigo: Llama Learns to Talk]] #MultiModal
+ [[https://github.com/huggingface/evaluation-guidebook][The LLM Evaluation guidebook ⚖️]]  #Evaluation #Pablo
+ [[https://ehudreiter.com/2022/06/01/error-annotations-to-evaluate/][Lets use error annotations to evaluate systems!]] #Evaluation #Pablo
+ [[https://arxiv.org/html/2303.05499v5][Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection]] #OpenSet #ObjectDetection
+ [[https://arxiv.org/pdf/2401.14159][Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks]] #OpenSet #SemanticSegmentation
+ [[https://digital-cousins.github.io/][ACDC: Automated Creation of Digital Cousins for Robust Policy Learning]] #DigitalCousins
+ [[https://arxiv.org/abs/2410.04289][Self-Supervised Anomaly Detection in the Wild: Favor Joint Embeddings Methods]] #SelfSupervisedLearning #AnomalyDetection #Joaquin #ProyectoADER
+ [[https://github.com/rhymes-ai/Aria?tab=readme-ov-file][ARIA : An Open Multimodal Native Mixture-of-Experts Model]] #Multimodal #MOE #VLM
+ [[https://newsletter.maartengrootendorst.com/p/a-visual-guide-to-mixture-of-experts][A Visual Guide to Mixture of Experts]] #LLMs #MOE
+ [[https://github.com/QwenLM/Qwen2-VL][Qwen2-VL]] #VLM
+ [[https://llava-vl.github.io/blog/2024-10-03-llava-critic/][LLaVA-Critic: Learning to Evaluate Multimodal Models]] #LLMAsaJudge #Multimodal
+ [[https://research.sign.mt/][Sign Language Processing]] #LSEAvatar
+ [[https://parlance-labs.com/education/][Educational resources on LLMs]] #LLMs #Course
+ [[https://arxiv.org/pdf/2407.07726][PaliGemma: A versatile 3B VLM for transfer]] #VLM
+ [[https://arxiv.org/abs/2310.18351][BioImage.IO Chatbot: A Community-Driven AI Assistant for Integrative Computational Bioimaging]] #Agents #Bioimage
+ [[https://link.springer.com/article/10.1007/s10815-023-02973-y][Artificial intelligence in time-lapse system: advances, applications, and future perspectives in reproductive medicine]] #Maria #IVF #TimeLapse
+ [[https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7732604/pdf/nihms-1648710.pdf][Automated Measurements of Key Morphological Features of Human Embryos for IVF]] #Maria #IVF

** Septiembre 2024

+ [[https://www.philschmid.de/fine-tune-multimodal-llms-with-trl][How to Fine-Tune Multimodal Models or VLMs with Hugging Face TRL]] #Accesibilidad #VLMs
+ [[https://arxiv.org/pdf/2409.11355][Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think]] #DepthEstimation #DiffusionModels
+ [[https://www.nature.com/articles/s41746-024-01258-7][A framework for human evaluation of large language models in healthcare derived from literature review]] #LLM #HumanEvaluation #Healthcare #ProyectoIA
+ [[https://besaya.infor.uva.es/sepln24/paper17.pdf][First Attempt to an Automatic Adaptation of Explanatory Structures in Spanish to Easy-to-Read]] #Easy2Read #PlenaInclusion #Mirari
+ [[https://arxiv.org/pdf/2409.14988][Beyond Fine-tuning: Unleashing the Potential of Continuous Pretraining for Clinical LLMs]] #MedicalLLMs #FineTuning #Prompting
+ [[https://www.arxiv.org/abs/2409.15334][Evaluating Large Language Models with Tests of Spanish as a Foreign Language: Pass or Fail?]] #ProyectoSara #SpanishEvaluation
+ [[https://www.arxiv.org/abs/2406.17789][Spanish and LLM Benchmarks: is MMLU Lost in Translation?]] #MachineTranslation #Limitations #ProyectoSara
+ [[https://arxiv.org/pdf/2409.15127][Boosting Healthcare LLMs Through Retrieved Context]] #MedicalLLMs #ProyectoIA
+ [[https://m.youtube.com/watch?v=bq1Plo2RhYI][Reliable, fully local RAG agents with LLaMA3.2-3b]] #RAG #Pablo #langgraph
+ [[https://arxiv.org/pdf/2409.14160][Hype, Sustainability, and the Price of the Bigger-is-Better Paradigm in AI]] #CIAIS
+ [[https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/][Llama 3.2: Revolutionizing edge AI and vision with open, customizable models]] #LLM #VLM
+ [[https://blog.google/intl/es-es/productos/presentamos-youtube-health-en-espana-para-conectar-a-las-personas-con-fuentes-sanitarias-autorizadas/][YouTube Health en España conecta a las personas con fuentes sanitarias autorizadas]] #ProyectoIA 
+ [[https://huggingface.co/papers/2409.16235][EuroLLM: Multilingual Language Models for Europe]] #LLMs #Multilingual
+ [[https://huggingface.co/papers/2409.12941][Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation]] #RAG #Pablo #Evaluation
+ [[https://arxiv.org/abs/2409.11242v1][Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse]] #RAG #Pablo #Evaluation
+ [[https://huggingface.co/blog/fine-video][FineVideo: behind the scenes]] #Video #DatasetConstruction
+ [[http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/article/view/6610][NoticIA: A Clickbait Article Summarization Dataset in Spanish]] #TeAhorroUnClick
+ [[https://arxiv.org/abs/2311.11077][Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning]] #FineTuning
+ [[https://arxiv.org/abs/2203.16082][Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech Recognition]] #Adapters #CatastrophicForgetting #ASR
+ [[http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/article/view/6611][Adaptación de ASR al habla de personas con síndrome de Down]] #ASR #Mirari #Accesibilidad
+ [[https://danielvanstrien.xyz/posts/post-with-code/colpali/2024-09-23-generate_colpali_dataset.html][Generating a dataset of queries for training and fine-tuning ColPali models on a UFO dataset]] #VLM #ProyectoIA #MultiModalRAG
+ [[https://github.com/dleemiller/WordLlama/tree/main][WordLlama]] #Embeddings #NLP #Pablo
+ [[https://research.google/blog/heal-a-framework-for-health-equity-assessment-of-machine-learning-performance/][HEAL: A framework for health equity assessment of machine learning performance]] #Ethics #Evaluation 
+ [[https://huggingface.co/blog/sql-console][Introducing the SQL Console on Datasets]]
+ [[https://huggingface.co/papers/2409.10516][RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval]] #RAG #LongContext
+ [[https://huggingface.co/blog/community-tools][Introducing Community Tools]]
+ [[https://www.rungalileo.io/hallucinationindex][A Ranking & Evaluation Framework For LLM Hallucinations]] #Pablo #RAG #LLMs
+ [[https://www.answer.ai/posts/2024-09-16-rerankers.html][rerankers: A Lightweight Python Library to Unify Ranking Methods]] #Pablo #Reranking #RAG
+ [[https://arxiv.org/abs/2409.07314][MEDIC: Towards a Comprehensive Framework for Evaluating LLMs in Clinical Applications]] #ProyectoIA #LLMs #Evaluation
+ [[https://mental.jmir.org/2024/1/e59479][The Opportunities and Risks of Large Language Models in Mental Health]] #Pablo #MentalHealth #Chatbot
+ [[https://blog.google/technology/health/google-ai-and-health/mental-health-google-ai-principles/?linkId=10939736][4 principles to guide AI in supporting mental health]] #Pablo #MentalHealth #Chatbot
+ [[https://colab.research.google.com/github/datacommonsorg/llm-tools/blob/master/notebooks/datagemma_rig.ipynb#scrollTo=tWMgvkQRHSet][Grounding LLM statistics facts using Retrieval Interleaved Generation (RIG)]] #RIG #Provenance 
+ [[https://aclanthology.org/2021.acl-long.88/][Explainable Prediction of Text Complexity: The Missing Preliminaries for Text Simplification]] #TextSimplification #Explainability
+ [[https://link.springer.com/article/10.1007/s13748-024-00325-0][Self-supervised approach for diabetic retinopathy severity detection using vision transformer]] #SelfSupervisedLearning #OPTRetina
+ [[https://arxiv.org/pdf/2408.16725][Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming]] #OmniModels
+ [[https://x.com/petebankhead/status/1833945619481985405][InstanSeg]] #Bioimage #Segmentation
+ [[https://huggingface.co/mistral-community/pixtral-12b-240910][pixtral-12b-240910 ]] #VLA
+ [[https://scopeblog.stanford.edu/2024/03/26/ai-large-language-models-doctors-patients/][Large language models in the clinic: AI enters the physician-patient mix]] #ProyectoIA
+ [[https://arxiv.org/abs/2409.06666][LLaMA-Omni: Seamless Speech Interaction with Large Language Models]] #OmniModels
+ [[https://aitp-conference.org/2024/slides/SW.pdf][A Few Open Problems in Neural Theorem Proving]] #TheoremProving #Lean
+ [[https://www.youtube.com/watch?v=wuZtUMEiKWY&list=PLZCA39VpuaZZ1cjH4vEIdXIb0dCpZs3Y5][YOLOv8: How to Train for Object Detection on a Custom Dataset]] #ObjectDetection
+ [[https://www.esade.edu/ecpol/es/publicaciones/cuando-la-ia-generativa-incrementa-la-desigualdad-evidencia-experimental-de-una-competicion-de-debates-universitarios/][Cuando la IA generativa incrementa la desigualdad: evidencia experimental de una competición de debates universitarios]] #ChatGPT #CIAIS
+ [[https://arxiv.org/pdf/2407.16117][A Logic for Veracity: Development and Implementation]] #Coq #Provenance
+ [[https://www.nature.com/articles/s42256-024-00889-5#data-availability][Accelerating histopathology workflows with generative AI-based virtually multiplexed tumour profiling]] #Bruno #Histopathology #SyntheticImages
+ [[https://ec.europa.eu/commission/presscorner/detail/es/ip_24_4123][Entrada en vigor de la Ley Europea de Inteligencia Artificial]] #CIAIS
+ [[https://github.com/merveenoyan/smol-vision][Smol Vision 🐣]] #ComputerVision #Optimisation #SmallModels
+ [[https://huangzhii.github.io/nuclei-HAI/][A pathologist–AI collaboration framework for enhancing diagnostic accuracies and efficiencies]] #Bruno #ActiveLearning #Pathology
+ [[https://huggingface.co/blog/anakin87/spectrum][Selective fine-tuning of Language Models with Spectrum]] #FineTuning #LLMs #Selective
+ [[https://github.com/huggingface/trl][TRL - Transformer Reinforcement Learning]] #ReinforcementLearning
+ [[https://openreview.net/forum?id=1cq9pmwRgG][Towards Safe Large Language Models for Medicine]] #LLM #Pablo
+ [[https://huggingface.co/learn/audio-course/chapter0/introduction][Welcome to the Hugging Face Audio course!]] #Audio #Mirari
+ [[https://huggingface.co/learn/audio-course/chapter7/transcribe-meeting][Transcribe a meeting]] #Diarization #Mirari
+ [[https://blog.haizelabs.com/posts/dspy/][Red-Teaming Language Models with DSPy]] #RedTeaming #DSPY #ProgrammingPromptEngineering

** Agosto 2024

+ [[https://huggingface.co/blog/synthetic-data-save-costs][Synthetic data: save money, time and carbon with open source]]  #SyntheticData #Mapi
+ [[https://huggingface.co/blog/cosmopedia][Cosmopedia: how to create large-scale synthetic data for pre-training]] #SyntheticData
+ [[https://huggingface.co/blog/image-similarity][Image Similarity with Hugging Face Datasets and Transformers]] #ImageRetrieval
+ [[https://huggingface.co/yifeihu/TB-OCR-preview-0.1][TB-OCR: an end-to-end OCR model handling text, math latex, and markdown formats all at once]] #OCR
+ [[https://amaarora.github.io/posts/2024-06-28%20ml-4M.html#image-retrieval-using-4m-21][Image retrieval app using Apple’s 4M-21 any-to-any vision model]] #imageretrieval #multimodality
+ [[https://eugeneyan.com/writing/llm-evaluators/][Evaluating the Effectiveness of LLM-Evaluators (aka LLM-as-Judge)]] #llm #Evaluation #pablo
+ [[https://www.vanderschaar-lab.com/why-tabular-foundation-models-should-be-a-research-priority/][Why Tabular Foundation Models Should Be a Research Priority]] #FoundationModels #TabularData
+ [[https://arxiv.org/abs/2406.18682][The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm]]  #Multilingual #RedTeaming #HarmReduction
+ [[https://github.com/rasbt/LLMs-from-scratch/blob/main/ch07/04_preference-tuning-with-dpo/dpo-from-scratch.ipynb][Direct Preference Optimization (DPO) for LLM Alignment (From Scratch)]] #LLMs #Alignment #DPO
+ [[https://arxiv.org/abs/2403.03893][From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models]] #ToxicityDetection #Multilingual
+ [[https://openai.com/index/gpt-4o-system-card/][GPT-4o System Card]] #modelcard #redteaming #seguridad
+ [[https://huggingface.co/papers/2408.08872][xGen-MM (BLIP-3): A Family of Open Large Multimodal Models]] #LMM #proyectoIA
+ [[https://www.answer.ai/posts/2024-08-13-small-but-mighty-colbert.html][Small but Mighty: Introducing answerai-colbert-small]] #InformationRetrieval #Rerankers #Pablo
+ [[https://martinfowler.com/articles/2024-restrict-algorithm.html][Instead of restricting AI and algorithms, make them explainable]] #CIAIS #Explicabilidad
+ [[https://fireworks.ai/blog/fireworks-quantization][How Fireworks evaluates quantization precisely and interpretably]] #Quantization #Evaluation 
+ [[https://newsletter.maartengrootendorst.com/p/a-visual-guide-to-mamba-and-state][A Visual Guide to Mamba and State Space Models]] #Mamba #Architecture
+ [[https://newsletter.maartengrootendorst.com/p/a-visual-guide-to-quantization][A Visual Guide to Quantization]] #Quantization
+ [[https://qwenlm.github.io/blog/qwen2-audio/][Qwen2-Audio: Chat with Your Voice!]] #Audio #Mirari
+ [[https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters][Adapting diffusion models]] #DiffusionModels #Personalization
+ [[https://blog.isaacmiller.dev/posts/dspy][Why I bet on DSPy]] #promptoptimization 
+ [[https://t.co/b8w40b6NIr][DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search]] #TheoremProving #lean #ReinforcementLearning
+ [[https://airisk.mit.edu/][What are the risks from Artificial Intelligence?]] #CIAIS #Ética #Riesgos
+ [[https://arxiv.org/abs/2408.12637][Building and better understanding vision-language models: insights and future directions]] #VLM #ProyectoIA
+ [[https://huggingface.co/blog/unified-tool-use][Tool Use, Unified]]  #LLM #ProyectoIA
+ [[https://huggingface.co/blog/unsung-heroes][The 5 Most Under-Rated Tools on Hugging Face]] #HuggingFace #Clases
+ [[https://huggingface.co/docs/transformers/en/tasks/monocular_depth_estimation][Monocular depth estimation]] #DepthEstimation
+ [[https://huggingface.co/docs/transformers/en/tasks/image_text_to_text][Image, text to text]] #VisualLanguageModels #ProyectoIA

** Julio 2024
+ [[https://arxiv.org/abs/2407.20046][Exploring Large Language Models to generate Easy to Read content]] #Easy2Read #Mirari #PlenaInclusion
+ [[https://arxiv.org/html/2310.02567v2][Improving Automatic VQA Evaluation Using Large Language Models]] #leo #prevenia #Pablo #metrics #Alignment 
+ [[https://ai.meta.com/blog/segment-anything-2/][Introducing SAM 2: The next generation of Meta Segment Anything Model for videos and images]] #segmentation #videos
+ [[https://huggingface.co/blog/smollm][SmolLM - blazingly fast and remarkably powerful]] #SmallLanguageModels
+ [[https://www.nationalgeographic.es/ciencia/2024/07/inteligencia-artificial-problemas-salud-mental-peligros-oportunidades-uso-chatbots][Cada vez más personas usan chatbots de inteligencia artificial para problemas de salud mental]] #Pablo #PrevenIA
+ [[https://github.com/stanfordnlp/dspy/blob/main/intro.ipynb][DSPy: Programming with Foundation Models]] #LanguageModels
+ [[https://arxiv.org/abs/2407.11144][YouTube-SL-25: A Large-Scale, Open-Domain Multilingual Sign Language Parallel Corpus]] #LSEAvatar
+ [[https://huggingface.co/blog/argilla-chatbot][How we leveraged distilabel to create an Argilla 2.0 Chatbot]] #Chatbot #Fine-Tuning #Pablo #PrevenIA
+ [[https://arxiv.org/pdf/1712.09923][What do we need to build explainable AI systems for the medical domain?]] #Explainability
+ [[https://huggingface.co/blog/dpo_vlm][Preference Optimization for Vision Language Models with TRL]] #VLM #ProyectoIA
+ [[https://huggingface.co/blog/winning-aimo-progress-prize][How NuminaMath Won the 1st AIMO Progress Prize]] #Mathematics #LLMs
+ [[https://huggingface.co/blog/presidio-pii-detection][Experimenting with Automatic PII Detection on the Hub using Presidio]] #CIAIS #PersonallyIdentifyingInformation
+ [[https://ollama.com/][Ollama: Get up and running with large language models.]] #LLMs #Inference
+ [[https://huggingface.co/blog/dpo_vlm][Preference Optimization for Vision Language Models with TRL]] #ProyectoIA #VisualLanguageModels
+ [[https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0305362][Building a framework for fake news detection in the health domain]] #MedicalFactChecking #Leo
+ [[https://lilianweng.github.io/posts/2024-07-07-hallucination/?utm_source=ainews&utm_medium=email&utm_campaign=ainews-to-be-named-3686][Extrinsic Hallucinations in LLMs]] #Hallucinations #LLMs
+ [[https://link.springer.com/article/10.1007/s13748-024-00326-z#Sec11][Advanced deep learning and large language models for suicide ideation detection on social media]] #SuicideIdeation #PrevenIA #Pablo
+ [[https://db.cs.cmu.edu/papers/2024/whatgoesaround-sigmodrec2024.pdf][What Goes Around Comes Around... And Around...]] #Databases
+ [[https://huggingface.co/spaces/KwaiVGI/LivePortrait][LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control]] #LSEAvatar #CopiaExpresiones 
+ [[http://www.sidar.org/ponencias/2007/egyrs/une139804/][Requisitos para el uso de la Lengua de Signos Espyearla en redes informáticas]] #LSEAvatar #TecnologiasAccesibles
+ [[https://www.rpdiscapacidad.gob.es/actualidad/noticias/0-504.htm][guías para elaborar materiales educativos accesibles]] #TecnologiasAccesibles
+ [[https://www.rpdiscapacidad.gob.es/estudios-publicaciones/2024_GuiaVideo.htm][Guía 6. Vídeos accesibles con subtitulado, audiodescripción y lengua de signos]] #LSEAvatar #TecnologiasAccesibles
+ [[https://x.com/akshay_pachaar/status/1808840963961598311][Faster RAG]] #RAG #Pablo
+ [[https://huggingface.co/papers/2304.08069][DETRs Beat YOLOs on Real-time Object Detection]] #ObjectDetection #RealTime
+ [[https://www.philschmid.de/fine-tune-embedding-model-for-rag][Fine-tune Embedding models for Retrieval Augmented Generation (RAG)]] #Pablo #RAG #PrevenIA
+ [[https://www.20minutos.es/noticia/5524396/0/importancia-lengua-signos-terapia-sesiones-mas-didacticas-mas-fluidas-mas-completas/][La importancia de la lengua de signos en terapia: sesiones más didácticas, más fluidas y más completas]] #LSEAvatar #TecnologiasAccesibles


** Junio 2024

+ [[https://www.youtube.com/watch?v=IoGaGfU1CIg][multimodal AI. open-source. in a nutshell.]] #MultiModal #ProyectoIA
+ [[https://www.youtube.com/watch?v=QaqX9B3jqYI][Supercharging RAG with Generative Feedback Loops from Weaviate]] #RAG
+ [[https://huggingface.co/papers/2311.06242][Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks]] #VisionLanguageModel #ProyectoIA
+ [[https://github.com/ganeshsar/UnityPythonMediaPipeAvatar][Unity + Python Google MediaPipe Avatar]] #LSEAvatar
+ [[https://arxiv.org/abs/2405.19660][PATIENT-Ψ: Using Large Language Models to Simulate Patients for Training Mental Health Professionals]] #Pablo #Chatbots #PrevenIA
+ [[https://github.com/ganeshsar/UnityPythonMediaPipeAvatar][Unity + Python Google MediaPipe Avatar]] #LSEAvatar #ProyectoIndra
+ [[https://www.spreadthesign.com/es.es/search/][Spreadthesign]] #LSEAvatar #ProyectoIndra
+ [[https://unianimate.github.io/][Unianimate]] #LSEAvatar #ProyectoIndra
+ [[https://www.nature.com/articles/s41597-023-02182-3][An annotated human blastocyst dataset to benchmark deep learning architectures for in vitro fertilization]] #Dataset #Maria [[https://figshare.com/articles/figure/Blastocyst_dataset_zip/20123153/3][Enlace]]
+ [[https://huggingface.co/docs/text-generation-inference/conceptual/streaming][Streaming]] #Pablo #Prevenia
+ [[https://qwenlm.github.io/blog/qwen2/][Hello Qwen2]] #LLM #Pablo #Prevenia
+ [[https://link.springer.com/article/10.1007/s11517-024-03131-x][Automatic text classification of prostate cancer malignancy scores in radiology reports using NLP models]] #TextClassification #Leo
+ [[https://github.com/huggingface/optimum-nvidia][https://github.com/huggingface/optimum-nvidia]] #Pablo #LLM #Optimization
+ [[https://www.tandfonline.com/doi/abs/10.1080/10447318.2024.2344355][An Empathic GPT-Based Chatbot to Talk About Mental Disorders With Spanish Teenagers]] #Pablo #Estancia
+ [[https://huggingface.co/spaces/HuggingFaceFW/blogpost-fineweb-v1][https://huggingface.co/spaces/HuggingFaceFW/blogpost-fineweb-v1]] #Datasets
+ [[https://medium.com/decodingml/llm-twin-course/home][Production-Ready LLM Twin Course]] #LanguageModels #Pablo
+ [[https://www.youtube.com/watch?v=hDa-M91MSGU][Fine-tune PaliGemma for image to JSON use cases]] #VisualLanguageModels #ProyectoIA
+ [[https://arxiv.org/abs/2405.15007][RE-Adapt: Reverse Engineered Adaptation of Large Language Models]] #InstructionTuning
+ [[https://huggingface.co/blog/NicoNico/green-bit-llm][GPU Poor Savior: Revolutionizing Low-Bit Open Source LLMs and Cost-Effective Edge Computing]] #LanguageModels #Quantization #FineTuning
+ [[https://huggingface.co/blog/falcon2-11b][Falcon 2: An 11B parameter pretrained language model and VLM, trained on over 5000B tokens and 11 languages]] #LanguageModel #VisualLanguageModel #ProyectoIA
+ [[https://colab.research.google.com/github/kamilakesbi/notebooks/blob/main/synthetic_pipeline_diarizers.ipynb#scrollTo=jA0Rh26gpxU7][🤗 Generate synthetic speaker diarization datas with Diarizers]] #Diarization #Mirari

** Mayo 2024

+ [[https://arxiv.org/abs/2405.17247][An Introduction to Vision-Language Modeling]] #VisionLanguageModels #ProyectoIA
+ [[https://www.aicrowd.com/challenges/meta-comprehensive-rag-benchmark-kdd-cup-2024][CRAG: Comprehensive RAG Benchmark]] #RAG #Pablo
+ [[https://jamanetwork.com/journals/jamanetworkopen/fullarticle/2818881][Use of Artificial Intelligence Chatbots in Interpretation of Pathology Reports]] #TextoClaro #Leo
+ [[https://github.com/TMElyralab/MusePose?tab=readme-ov-file][MusePose: a Pose-Driven Image-to-Video Framework for Virtual Human Generation]] #LenguaSignos #ProyectoINDRA
+ [[https://arxiv.org/pdf/2405.10718][SignLLM: Sign Languages Production Large Language Models]] [[https://signllm.github.io/][GitHub]] #LenguaSignos #ProyectoINDRA
+ [[https://www.inclusion-europe.eu/wp-content/uploads/2017/06/ES_Information_for_all.pdf][Información para todos Las reglas europeas para hacer información fácil de leer y comprender]] #Mirari #PlenaInclusion
+ [[https://arxiv.org/abs/2212.09720][The case for 4-bit precision: k-bit Inference Scaling Laws]] #Quantization
+ [[https://www.accessible-social.com/][Accessible Social]] #Accesibilidad #Mirari
+ [[https://huggingface.co/blog/danaaubakirova/doc-augmentation][Multimodal Augmentation for Documents: Recovering “Comprehension” in “Reading and Comprehension” task]] #DocumentAnalysis
+ [[https://huggingface.co/blog/paligemma][PaliGemma – Google's Cutting-Edge Open Vision Language Model]] #Vision
+ [[https://glosario.pikaramagazine.com/inicio.php?lg=es&sec=inicio][Glosario Lengua de Signos Espyearla]] #LSE #Mirari #LecturaFacil
+ [[https://huggingface.co/meta-llama/Meta-Llama-Guard-2-8B][Meta Llama Guard 2]] #Pablo #Guards
+ [[https://twitter.com/__kolesnikov__/status/1790464234330972239][Finetune PaliGemma]] #Vision #ImageCaptioning #PlenaInclusion #Mirari
+ [[https://github.com/huggingface/diarizers][Diarizers]] #Diarization #Mirari #Sara
+ [[https://arxiv.org/abs/2405.07988][A Generalist Learner for Multifaceted Medical Image Interpretation]] #ProyectoIA 
+ [[https://arxiv.org/abs/2405.07960][AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments]] #ProyectoIA 
+ [[https://twitter.com/HugoLaurencon/status/1787500741071880677][ Idefics2 ]] #ProyectoIA #VisualLanguageModel

** Abril 2024

+ [[https://huggingface.co/blog/jat][Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent]] #MultiModal #Agents
+ [[https://www.answer.ai/posts/2024-03-06-fsdp-qlora.html][You can now train a 70b language model at home]] #Training #LLMs
+ [[https://arxiv.org/abs/2404.08676][ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming]] #RedTeaming #Pablo #Evaluacion
+ [[https://arxiv.org/abs/2404.12272][Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences]] #Pablo #LLM #Validation
+ [[https://academic.oup.com/humrep/article/37/10/2275/6659059][Embryologist agreement when assessing blastocyst implantation probability: is data-driven prediction the solution to embryo assessment subjectivity?]] #Maria
+ [[https://academic.oup.com/humrep/advance-article/doi/10.1093/humrep/deae064/7643856?login=true][Generative artificial intelligence to produce high-fidelity blastocyst-stage embryo images ]] #Maria
+ [[https://weaviate.io/blog/dspy-optimizers][Your Language Model Deserves Better Prompting]] #Prompting #Pablo
+ [[https://huggingface.co/projecte-aina/FlorRAG][FLOR-6.3B Model optimized for Retrieval Augmented Generation]] #Rag #Pablo
+ [[https://huggingface.co/blog/gigant/vlm-design][Design choices for Vision Language Models in 2024]] #VisionLanguageModels #ProyectoIA
+ [[https://arxiv.org/pdf/2404.08940.pdf][Introducing Super RAGs in Mistral 8x7B-v1]] #Pablo #RAG #ProyectoIA
+ [[https://github.com/openvinotoolkit/anomalib/blob/main/README.md][A library for benchmarking, developing and deploying deep learning anomaly detection algorithms]] #AnomalyDetection #Bruno
+ [[https://huggingface.co/blog/idefics2][Introducing Idefics2: A Powerful 8B Vision-Language Model for the community]] #ImageCaptioning #VisionModels #Mirari #Accesibilidad
+ [[https://coconut-mode.com/posts/ring-attention/][Ring Attention Explained]] #LLM
+ [[https://huggingface.co/blog/vlms][Vision Language Models Explained]] #VisionModels #Mirari #Accesibilidad
+ [[https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7360969/#rmb212331-bib-0003][Development of an automated two pronuclei detection system on time‐lapse embryo images using deep learning techniques]] #María
+ [[https://www.youtube.com/watch?v=eMlx5fFNoYc][Visualizing Attention]] #LLM #Docencia
+ [[https://stability.ai/news/introducing-stable-lm-2-12b][Introducing Stable LM 2 12B]] #Pablo #LLM
+ [[https://proceedings.neurips.cc/paper_files/paper/2023/hash/47f30d67bce3e9824928267e9355420f-Abstract-Conference.html][LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation]] #Image2Text #Evaluation
+ [[https://ovarianresearch.biomedcentral.com/articles/10.1186/s13048-024-01376-6][A novel machine-learning framework based on early embryo morphokinetics identifies a feature signature associated with blastocyst development]] #Maria #Embriones
+ [[https://huggingface.co/spaces/prs-eth/marigold-lcm][Marigold-LCM Depth Estimation]] #DepthEstimation #Angela
+ [[https://arxiv.org/abs/2306.14824][Kosmos-2: Grounding Multimodal Large Language Models to the World]] #Accesibilidad #ProyectoIA #Mirari
+ [[https://arxiv.org/abs/2311.05550][Towards End-to-End Spoken Grammatical Error Correction]] #ASR #Mirari
+ [[https://www.biorxiv.org/content/10.1101/2024.04.06.587952v1][Transformers do not outperform Cellpose]] #CellSegmentation #HackathonMadrid
+ [[https://www.972mag.com/lavender-ai-israeli-army-gaza/][Lavender’: The AI machine directing Israel’s bombing spree in Gaza]] #CIAIS
+ [[https://towardsdatascience.com/advanced-retrieval-augmented-generation-from-theory-to-llamaindex-implementation-4de1464a9930][Advanced Retrieval-Augmented Generation: From Theory to LlamaIndex Implementation]] #RAG #Pablo
+ [[https://vickiboykis.com/what_are_embeddings/][What are embeddings?]] #Embeddings
+ [[https://www.crue.org/publicacion/la-inteligencia-artificial-generativa-en-la-docencia-universitaria/][La Inteligencia Artificial Generativa en la Docencia Universitaria]] #IA #Docencia
+ [[https://huggingface.co/blog/quanto-introduction][Quanto: a pytorch quantization toolkit]] #quantization
+ [[https://huggingface.co/blog/arena-lighthouz][Introducing the Chatbot Guardrails Arena]] #GuardRails #Evaluation
+ [[https://huggingface.co/docs/transformers/main/en/model_doc/llava_next][LLaVA-NeXT]] #ProyectoIA #Accesibilidad 
+ [[https://huggingface.co/blog/cosmopedia][Cosmopedia: how to create large-scale synthetic data for pre-training]] #SyntheticData #NLP

** Marzo 2024

+ [[https://vickiboykis.com/what_are_embeddings/][What are embeddings]] #Embeddings
+ [[https://arxiv.org/abs/2310.11511?s=09][Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection]] #RAG
+ [[https://arxiv.org/pdf/2304.03284.pdf][SegGPT: Segmenting Everything In Context]] #SemanticSegmentation
+ [[https://huggingface.co/blog/watermarking][AI Watermarking 101: Tools and Techniques]] #watermarking #CIAIS
+ [[https://huggingface.co/blog/how-to-generate][How to generate text: using different decoding methods for language generation with Transformers]] #Transformers #Decoding #Master
+ [[https://comunicacionclara.com/docs/guia-comunicacion-clara-prodigioso-volcan.pdf][El derecho a entender]] #LecturaFacil #Mirari
+ [[https://www.iso.org/obp/ui/en/#iso:std:iso-iec:23859:ed-1:v1:en][ISO/IEC 23859:2023(en) Information technology — User interfaces — Requirements and recommendations on making written text easy to read and understand]] #LecturaFacil #Mirari
+ [[https://www.iso.org/obp/ui/en/#iso:std:iso:24495:-1:ed-1:v1:en][ISO 24495-1:2023(en) Plain language — Part 1: Governing principles and guidelines]] #LecturaFacil #Mirari
+ [[https://olgacarreras.blogspot.com/2024/02/libro-accesibilidad-web-wcag-22-de.html][Libro "Accesibilidad Web. WCAG 2.2 de forma sencilla". Descarga gratuita.]] #AccesibilidadWeb #LecturaFacil #Mirari

** Febrero 2024

+ [[https://arxiv.org/abs/2402.13616][YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information]] #ObjectDetection
+ [[https://www.mdpi.com/1424-8220/24/5/1472][Synthetic Corpus Generation for Deep Learning-Based Translation of Spanish Sign Language]] #LenguaSignos
+ [[https://ai4k12.org/][The Artificial Intelligence (AI) for K-12 initiative (AI4K12) is jointly sponsored by AAAI and CSTA]] #ArtificialIntelligence #Courses
+ [[https://speechbrain.github.io/index.html][SpeechBrain Open-Source Conversational AI for Everyone]] #Audio #Mirari
+ [[https://www.biorxiv.org/content/10.1101/2024.02.10.579780v1][Cellpose3: one-click image restoration for improved cellular segmentation]] #Arrate #Segmentación #Adrián
+ [[https://www.biorxiv.org/content/10.1101/2024.02.03.576026v1.full.pdf][BiaPy: A unified framework for versatile bioimage analysis with deep learning]] #Arrate #Adrian

** Enero 2024

+ [[https://huggingface.co/blog/constitutional_ai][Constitutional AI]] #Pablo #Guardrails
+ [[https://huggingface.co/blog/patchtsmixer][PatchTSMixer in HuggingFace - Getting Started]] #Neuroenergia
+ [[https://huggingface.co/blog/patchtst][Patch Time Series Transformer in Hugging Face - Getting Started]] #Neuroenergia
+ [[https://huggingface.co/papers/2401.02994][Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM]] #Chats
+ [[https://wanglab.ai/u-mamba.html][U-Mamba Enhancing Long-range Dependency for Biomedical Image Segmentation]] #Segmentation
+ [[https://pubmed.ncbi.nlm.nih.gov/35280929/][How Useful Is Image-Based Active Learning for Plant Organ Segmentation?]] #ActiveLearning
+ [[https://arxiv.org/abs/2302.04075][Best Practices in Active Learning for Semantic Segmentation]] #ActiveLearning 
+ [[https://justraigs.grand-challenge.org/][Justified Referral in AI Glaucoma Screening]] #OPTRetina
+ [[https://www.youtube.com/watch?v=nOxKexn3iBo][Getting Started With CUDA for Python Programmers]] #CUDA
+ [[https://www.sciencedirect.com/science/article/pii/S2666914523000325][Characteristics of a Large, Labeled Data Set for the Training of Artificial Intelligence for Glaucoma Screening with Fundus Photographs]] #OPTRetina #Glaucoma
+ [[https://osanseviero.github.io/hackerllama/blog/posts/sentence_embeddings2/][Sentence Embeddings. Cross-encoders and Re-ranking]] #Embeddings #Pablo
+ [[https://www.ub.edu/edap/?page_id=2898][MANIFIESTO POR UN LENGUAJE CLARO EN LA ADMINISTRACIÓN]] #LenguajeClaro
+ [[https://arxiv.org/pdf/2306.11644.pdf][Textbooks Are All You Need]] #ProyectoNacional
+ [[https://academic.oup.com/bioinformatics/article/37/21/3856/6313159?login=true][Medical concept normalization in clinical trials with drug and disease representation learning ]] #Leo #Normalization
+ [[https://huggingface.co/papers/2401.10225][ChatQA: Building GPT-4 Level Conversational QA Models]] #Pablo #ChatBots
+ [[https://arxiv.org/abs/2401.08417][Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation]] #Translation #ClaraMED
+ [[https://cognitiveresearchjournal.springeropen.com/articles/10.1186/s41235-023-00529-3][The impact of AI errors in a human-in-the-loop process]] #CIAIS #Bias #HumanInTheLoop
+ [[https://twitter.com/yoachlacombe/status/1744447885255614661][Text to Speech]] #Text2Speech #TTS #Mirari #Leo
+ [[https://twitter.com/predict_addict/status/1740642688829944049?s=20][TSPP: A Unified Benchmarking Tool for Time-series Forecasting]] #TimeSeriesForecasting #Neuroenergía
+ [[https://arxiv.org/abs/2107.13586][Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing]] #Prompting
+ [[https://www.philschmid.de/fine-tune-llms-in-2024-with-trl][How to Fine-Tune LLMs in 2024 with Hugging Face]] #FineTuning #LLM
+ [[https://huggingface.co/zero-gpu-explorers][ZeroGPU Spaces]] #Hardware #HuggingFace
+ [[https://www.nature.com/articles/s41591-023-02702-z?utm_source=substack&utm_medium=email][A deep learning system for predicting time to progression of diabetic retinopathy]] #OPTRetina #RetinalProgression
+ [[https://huggingface.co/posts/osanseviero/691474247332404][Merge Large Language Models with mergekit comparison]] #ModelMerge
+ [[https://huggingface.co/blog/mlabonne/merge-models][Merge Large Language Models with mergekit]] #ModelMerge
+ [[https://aijblog.notion.site/Intro-to-ColBERT-v2-e1620a3c5e8747cd9f52ef8bbd5538bf][Intro to ColBERT - v2]] #Retrieval #Pablo
+ [[https://github.com/bclavie/RAGatouille][Welcome to RAGatouille]] #Retrieval #Pablo
+ [[https://sander.ai/2014/08/05/spotify-cnns.html][Recommending music on Spotify with deep learning]] #Audio #RecommendationSystems
+ [[https://biii.eu/cellpose][cellpose]] [[https://www.nature.com/articles/s41592-020-01018-x][Cellpose: a generalist algorithm for cellular segmentation]] [[https://github.com/MouseLand/cellpose][GitHub]] #SueAnn
+ [[https://arxiv.org/abs/2305.18290][Direct Preference Optimization: Your Language Model is Secretly a Reward Model]] #Training #PreferenceModels
+ [[https://arxiv.org/abs/2401.00368][Improving Text Embeddings with Large Language Models]] #TextEmbeddings
+ [[https://huggingface.co/blog/red-teaming][Red-Teaming Large Language Models]] #Pablo #RedTeaming
+ [[https://arxiv.org/abs/2307.09288][Llama 2: Open Foundation and Fine-Tuned Chat Models]] #RedTeaming #LLMs
+ [[https://arxiv.org/abs/2304.01373][Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling]] #Transformers #Training
+ [[https://osanseviero.github.io/hackerllama/blog/posts/random_transformer/][The Random Transformer]] #Transformers
+ [[https://arxiv.org/abs/2401.00908][DocLLM: A layout-aware generative language model for multimodal document understanding]] #Documents #MultiModal
+ [[https://www.tandfonline.com/doi/abs/10.1080/17686733.2019.1619355][Exploring deep learning networks for tumour segmentation in infrared images]] #Zataca #ThermalImaging
+ [[https://link.springer.com/article/10.1007/s00521-021-06372-1][Thermal-based early breast cancer detection using inception V3, inception V4 and modified inception MV4]] #Zataca #ThermalImaging
+ [[https://ieeexplore.ieee.org/abstract/document/9261422][A Systematic Review of Breast Cancer Detection Using Thermography and Neural Networks]] #Zataca #ThermalImaging
+ [[https://huggingface.co/papers/2401.01055][LLaMA Beyond English: An Empirical Study on Language Capability Transfer]] #MultiLingual #NLP
+ [[https://www.sciencedirect.com/science/article/pii/S1568494621011303?via%3Dihub#fig3][End-to-end multi-task learning for simultaneous optic disc and cup segmentation and glaucoma classification in eye fundus images]] #OPTRetina #Angela
+ [[https://osf.io/preprints/socarxiv/jqxb6][Pygmalion Displacement: When Humanising AI Dehumanises Women]] #CIAIS
+ [[https://arxiv.org/abs/2310.16764][ConvNets Match Vision Transformers at Scale]] #NFNet #ComputerVision
+ [[https://arxiv.org/abs/2311.11045?utm_source=substack&utm_medium=email][Orca 2: Teaching Small Language Models How to Reason]] #LanguageModel #Prompting
+ [[https://pub.towardsai.net/advanced-rag-techniques-an-illustrated-overview-04d193d8fec6][Advanced RAG Techniques: an Illustrated Overview]] #RAG #Pablo
+ [[https://www.plenainclusionlarioja.org/publicaciones/publicaciones-plena-inclusion-la-rioja][Publicaciones Plena Inclusión]] #LecturaFacil
+ [[https://huggingface.co/papers/2312.17120][Generative AI for Math: Part I -- MathPile: A Billion-Token-Scale Pretraining Corpus for Math]] #Dataset #ProyectoIA
+ [[https://pubmed.ncbi.nlm.nih.gov/33219237/][The SUSTech-SYSU dataset for automated exudate detection and diabetic retinopathy grading]] #OPTRetina #Segmentation [[https://figshare.com/articles/dataset/The_SUSTech-SYSU_dataset_for_automated_exudate_detection_and_diabetic_retinopathy_grading/12570770/1][Dataset]]
+ [[https://github.com/valeman/awesome-conformal-prediction][Awesome Conformal Prediction]] #ConformalPrediction
+ [[https://twitter.com/reach_vb/status/1742075640990322689][OpenVoice]] #Mirari

** Diciembre 2023

+ [[https://www.frontiersin.org/articles/10.3389/frai.2023.1323924/full][Development and evaluation of multimodal AI for diagnosis and triage of ophthalmic diseases using ChatGPT and anterior segment images: protocol for a two-stage cross-sectional study]] #ProyectoIA #OPTRetina
+ [[https://arxiv.org/abs/2311.17136][UniIR: Training and Benchmarking Universal Multimodal Information Retrievers]] #Retrieval #MultiModal
+ [[https://arxiv.org/abs/2311.16452][Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine]] #ProyectoIA #Pablo #Prompting
+ [[https://stability.ai/research/adversarial-diffusion-distillation][Adversarial Diffusion Distillation]] #Distillation #DataGeneration
+ [[https://arxiv.org/abs/2312.06709][AM-RADIO: Agglomerative Model -- Reduce All Domains Into One]] #Distillation #VisualFundationModel #ProyectoIA
+ [[https://arxiv.org/abs/2312.06635][Gated Linear Attention Transformers with Hardware-Efficient Training]] #Transformers
+ [[https://jamanetwork.com/journals/jamanetworkopen/fullarticle/2812964][Development of Deep Ensembles to Screen for Autism and Symptom Severity Using Retinal Photographs]] #OPTRetina
+ [[https://huggingface.co/blog/assisted-generation][Assisted Generation: a new direction toward low-latency text generation]] #Optimization #Pablo
+ [[https://huggingface.co/blog/whisper-speculative-decoding][Speculative Decoding for 2x Faster Whisper Inference]] #Optimization #Mirari #Pablo
+ [[https://arxiv.org/abs/2311.05112][A Survey of Large Language Models in Medicine: Principles, Applications, and Challenges]] #ProyectoIA
+ [[https://arxiv.org/abs/2312.07814][A Foundational Multimodal Vision Language AI Assistant for Human Pathology]] #ProyectoIA
+ [[https://www.sciencedirect.com/science/article/pii/S1361841522003322?via%3Dihub#sec3][Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging]] #DataSinthesis #Manuel #GANS
+ [[https://vgel.me/posts/faster-inference/][How to make LLMs go fast]] #Optimizations #Transformers
+ [[https://arxiv.org/abs/2312.04746][Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos]] #ProyectoIA
+ [[https://mbzuai-oryx.github.io/GeoChat/][GeoChat: Grounded Large Vision-Language Model for Remote Sensing]] #ProyectoIA
+ [[https://www.nature.com/articles/s41592-023-02083-8][Uncovering developmental time and tempo using deep learning]] #Maria
+ [[https://www.nature.com/articles/s41592-023-01873-4][EmbryoNet: using deep learning to link embryonic phenotypes to signaling pathways]] #Maria
+ [[https://www.nature.com/collections/ejcfiieddc][Method of the Year 2023: Methods for modeling development]] #Maria
+ [[https://bmcbiol.biomedcentral.com/articles/10.1186/s12915-022-01372-6][Segmentation, tracking and cell cycle analysis of live-cell imaging data with Cell-ACDC]] #CellSegmentation #Maria [[https://github.com/SchmollerLab/Cell_ACDC][Software]]
+ [[https://www.microsoft.com/en-us/research/blog/the-power-of-prompting/][The Power of Prompting]] #Prompting #Pablo
+ [[https://github.com/microsoft/promptbase][promptbase]] #Prompting
+ [[https://www.microsoft.com/en-us/research/blog/steering-at-the-frontier-extending-the-power-of-prompting/][Steering at the Frontier: Extending the Power of Prompting]] #Prompting
+ [[https://www.anyscale.com/blog/a-comprehensive-guide-for-building-rag-based-llm-applications-part-1][Building RAG-based LLM Applications for Production]] #RAG #Pablo
+ [[https://lightning.ai/pages/community/tutorial/pytorch-memory-vit-llm/][Optimizing Memory Usage for Training LLMs and Vision Transformers in PyTorch - Lightning AI]] #Optimization #Training
+ [[https://weaviate.io/blog/multimodal-rag][Multimodal Retrieval Augmented Generation(RAG)]] #MultiModal #RAG
+ [[https://huggingface.co/blog/optimum-nvidia][Optimum-NVIDIA on Hugging Face enables blazingly fast LLM inference in just 1 line of code]] #LLM #Efficiency #Pablo
+ [[https://huggingface.co/blog/mixtral][Welcome Mixtral - a SOTA Mixture of Experts on Hugging Face]] #Pablo
+ [[https://arxiv.org/abs/2306.11925][LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching]] #ProyectoIA #SelfSupervisedLearning #OPTRetina
+ [[https://huggingface.co/blog/moe][Mixture of Experts Explained]] #LLM #Pablo
+ [[https://www.nature.com/articles/s41592-022-01655-4][PyImageJ: A library for integrating ImageJ and Python]] #ImageJ #Arrate #Adrian
+ [[https://www.retinalphysician.com/issues/2023/october-2023/updates-in-the-diabetic-retinopathy-screening-land][Updates in the Diabetic Retinopathy Screening Landscape]] #OPTRetina
+ [[https://ieeexplore.ieee.org/abstract/document/9815506][Full-Resolution Network and Dual-Threshold Iteration for Retinal Vessel and Coronary Angiograph Segmentation]] #OPTRetina [[https://github.com/lseventeen/FR-UNet][Code]]
+ [[https://www.mdpi.com/2504-2289/7/1/25][A Novel Approach for Diabetic Retinopathy Screening Using Asymmetric Deep Learning Features]] #OPTRetina
+ [[https://www.sciencedirect.com/science/article/pii/S0957417423000581][Diabetic retinopathy identification using parallel convolutional neural network based feature extractor and ELM classifier]] #OPTRetina
+ [[https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10145952/][Retinal Disease Detection Using Deep Learning Techniques: A Comprehensive Review]] #OPTRetina
+ [[https://mistral.ai/news/mixtral-of-experts/][Mixtral of experts A high quality Sparse Mixture-of-Experts.]] #LLM
+ [[https://github.com/royerlab/napari-chatgpt][napari-chatgpt]] #Adrian #Agente
+ [[https://autelsinsights.es/claves-para-la-gobernanza-de-sistemas-de-inteligencia-artificial/][Claves para la Gobernanza de sistemas de Inteligencia Artificial]] #Gobernanza #ProyectoNacional
+ [[https://arxiv.org/abs/2311.16079][MEDITRON-70B: Scaling Medical Pretraining for Large Language Models]] #ProyectoIA [[https://t.co/JWUFy2i384][trainer code]] #Corpus
+ [[https://ai.meta.com/research/publications/robbie-robust-bias-evaluation-of-large-generative-language-models/][ROBBIE: Robust Bias Evaluation of Large Generative Language Models]] #Bias #PromptBasedMetrics
+ [[https://ai.meta.com/research/seamless-communication/?utm_source=twitter&utm_medium=organic_social&utm_campaign=fair10&utm_content=thread][Seamless Communication]] #Audio #Mirari
+ [[https://arxiv.org/abs/2311.16989][ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?]] #LLMs #Challenges
+ [[https://blog.langchain.dev/deconstructing-rag/][Deconstructing RAG]] #Pablo #RAG
+ [[https://huggingface.co/collections/facebook/seamless-communication-6568d486ef451c6ba62c7724][Seamless Communication]] #Mirari #Speech2Speech #Speech2Text

** Noviembre 2023

+ [[https://www.trulens.org/][Evaluate and Track LLM Applications]] #Pablo #RAG #Evaluation
+ [[https://deepmind.google/discover/blog/millions-of-new-materials-discovered-with-deep-learning/][Millions of new materials discovered with deep learning]] #Science #GNN [[https://deepmind.google/discover/blog/millions-of-new-materials-discovered-with-deep-learning/][Paper]]
+ [[https://docs.google.com/presentation/d/1hQUd3pF8_2Gr2Obc89LKjmHL0DlH-uof9M0yFVd3FA4/mobilepresent?slide=id.g16197112905_0_0][Some intuitions about large language models]] #LLM 
+ [[https://twitter.com/yoachlacombe/status/1729873482975170920][Finetuning TTS]] #Text2Speech #Mirari
+ [[https://huggingface.co/collections/ylacombe/text-to-speech-datasets-65674c292d738342786b4528][Text-To-Speech datasets]] #Text2Speech #Mirari
+ [[https://signon-project.eu/wp-content/uploads/2021/06/DeCoster_Isolated_CVPRW_2021_OpenAccess.pdf][Isolated Sign Recognition from RGB Video using Pose Flow and Self-Attention]] #LenguaSignos [[https://cvml.ankara.edu.tr/datasets/][Dataset]]
+ [[https://signon-project.eu/wp-content/uploads/2022/01/AICS2021_paper_final.pdf][Sign Language Fingerspelling Recognition using
Synthetic Data]] #LenguaSignos
+ [[http://www.lrec-conf.org/proceedings/lrec2020/workshops/SIGN2020/pdf/2020.signlanglrec-1.8.pdf][LSE_UVIGO: A Multi-source Database for Spanish Sign Language Recognition]] #LenguaSignos #Dataset
+ [[https://www.sciencedirect.com/science/article/pii/S0957417422020115][A survey on Sign Language machine translation]] #LenguaSignos #Survey
+ [[https://www.youtube.com/watch?v=vZTvzEuOhMk][Great Practices for Retrieval Augmented Generation (RAG) in Production]] #RAG #Pablo
+ [[https://medium.com/@sangotechnology1/chat-with-your-youtube-video-78a463776528][Chat with your Youtube video]] #Adrian #YoutubeChat
+ [[https://betterprogramming.pub/youtube-chatbot-using-langchain-and-openai-f8faa8f34929][YouTube Chatbot using LangChain and OpenAI]] #Adrian #YoutubeChat
+ [[https://github.com/emmethalm/youtube-to-chatbot][Youtube to chatbot]] #Adrian #YoutubeChat
+ [[https://escueladepacientes.es/mi-enfermedad/ostomias/colostomias-e-ileostomias][Escuela de pacientes]] #Adrian #YoutubeChat 
+ [[https://huggingface.co/papers/2311.16079][MEDITRON-70B: Scaling Medical Pretraining for Large Language Models]] #ProyectOIA
+ [[https://arxiv.org/abs/2311.04886][SEMQA: Semi-Extractive Multi-Source Question Answering]] #QuestionAnswering #RAG
+ [[https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8999113&casa_token=aTTC32z3P5YAAAAA:SEBGfTGb2fa2HaFDyOpNz3u2G9VfU21RNSY4Bqt5ki5GzhdcpqA7-J62T_ecSP_8fJ6CxAUhC7M&tag=1][Comprehend Medical: a Named Entity Recognition and Relationship Extraction Web Service]] #ClaraMed #EntityRelation
+ [[https://ieeexplore.ieee.org/abstract/document/9892285][Named Entity Recognition for Audio De-Identification]] #Mirari #Anonimization
+ [[https://github.com/feldberlin/timething][Timething]] #Mirari #TextAlignment
+ [[https://blog.langchain.dev/applying-openai-rag/][Applying OpenAI's RAG Strategies]] #RAG #Pablo
+ [[https://arxiv.org/abs/2311.11077][Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning]] #FineTuning #NLP
+ [[https://odsc.com/blog/building-named-entity-recognition-and-relationship-extraction-components-with-huggingface-transformers/?utm_campaign=Learning%20Posts&utm_content=200655503&utm_medium=social&utm_source=twitter&hss_channel=tw-1357730263481122817][Building Named Entity Recognition and Relationship Extraction Components with HuggingFace Transformers]] #NER #ER #ClaraMed
+ [[https://alz-journals.onlinelibrary.wiley.com/doi/10.1002/alz.13529][Retina pathology as a target for biomarkers for Alzheimer's disease: Current status, ophthalmopathological background, challenges, and future directions]] #OPTRetina #Alzheimer
+ [[https://weaviate.io/blog/rag-evaluation][An Overview on RAG Evaluation]] #RAG #Pablo
+ [[https://menhir-project.eu/index.php/links/][Proyecto Menhir]] #PrevenIA #Pablo
+ [[https://arxiv.org/abs/2310.15135][Quantifying the Dialect Gap and its Correlates Across Languages]] #ASR #Mirari
+ [[https://www.nature.com/articles/s41467-023-42664-x][Evolutionary design of explainable algorithms for biomedical image segmentation]] #ImageProcessing #Segmentation #EvolutionaryAlgorithms
+ [[https://github.com/run-llama/llama_index/tree/main/docs/examples][Llama index examples]] #Tutorials #LLMs
+ [[https://huggingface.co/blog/JMJM/giskard-llm-testing-and-debugging-hf][Introducing the Giskard Bot: Enhancing LLM Testing & Debugging on Hugging Face]] #Vulnerabilities #LLMDebugging
+ [[https://garibida.github.io/cross-image-attention/][Cross-Image Attention for Zero-Shot Appearance Transfer]] #Manu #StyleTransfer
+ [[https://stop-project.github.io/][STOP: Suicide prevenTion in sOcial Platforms]] #SUicidio #Pablo 
+ [[https://www.gladia.io/blog/gladia-speech-to-text-api-speaker-diarization][Gladia Speech-to-Text API: Speaker Diarization]] #Diarization #Mirari

** Octubre 2023 

+ [[https://huggingface.co/models?other=metaclip][MetaClip]] #ImageCaptioning #Embeddings
+ [[https://github.com/langchain-ai/langsmith-cookbook/blob/main/testing-examples/using-fixed-sources/using_fixed_sources.ipynb][RAG Evaluation using Fixed Sources]] #RAG #Pablo
+ [[https://github.com/nielsrogge/transformers-tutorials][Transformers-Tutorials]] #Transformers #Tutorials
+ [[https://github.com/coqui-ai/TTS/tree/v0.19.0][Coqui TTS]] #Text2Speech #Mirari
+ [[https://praeclarumjj3.github.io/oneformer/][OneFormer: One Transformer to Rule Universal Image Segmentation]] #SemanticSegmentation
+ [[https://arxiv.org/pdf/2102.06171.pdf][High-Performance Large-Scale Image Recognition Without Normalization]] #ImageClassificaiton
+ [[https://simonwillison.net/2023/Oct/23/embeddings/][Embeddings: What they are and why they matter]] #Embeddings #Pablo #Master
+ [[https://github.com/run-llama/llama_index/blob/main/docs/examples/multi_modal/llava_multi_modal_tesla_10q.ipynb][Retrieval-Augmented Image Captioning]] #RAG #ImageCaptioning #MultiModal
+ [[https://dataprovenance.org/][Data Provenance Explorer]] #DataProvenance
+ [[https://ceur-ws.org/Vol-3516/paper19.pdf][CLEAR.TEXT Enhancing the Modernization Public Sector Organizations by Deploying Natural Language Processing to Make Their Digital Content CLEARER to Those with Cognitive Disabilities]] #LecturaFacil #Mirari
+ [[https://ceur-ws.org/Vol-3516/paper13.pdf][IRAZ: Easy-to-Read Content Generation via Automated Text Simplification]] #LecturaFacil #Mirari
+ [[https://ceur-ws.org/Vol-3516/paper01.pdf][OBSER‐MENH: Digital OBSERvatory of MENtal Health in Social Networks for Healthcare Institutions Based on Language Technologies]] #PrevenIA #Pablo
+ [[https://arxiv.org/pdf/2305.06813.pdf][Generation of Structurally Realistic Retinal Fundus Images with Diffusion Models]] #OPTRetina #DifussionModels
+ [[https://selfrag.github.io/][Self-RAG: Learning to Retrieve, Generate and Critique through Self-Reflections]] #RAG #PrevenIA #Pablo
+ [[https://huggingface.co/blog/gradio-lite][Gradio-Lite: Serverless Gradio Running Entirely in Your Browser]] #Master #Gradio #Interfaces
+ [[https://huggingface.co/blog/Andyrasika/samantha-and-mistral-7b][Samantha and Mistral 7B: A Powerful and Versatile Language Model Duo]] #PrevenIA #Pablo
+ [[https://www.adept.ai/blog/fuyu-8b][Fuyu-8B: A Multimodal Architecture for AI Agents]] #MultiModality
+ [[https://lawsofux.com/es/][Laws of UX]] #Usabilidad
+ [[https://thesequence.substack.com/p/inside-opro-google-deepminds-new?utm_source=post-email-title&publication_id=54309&post_id=138099496&utm_campaign=email-post-title&isFreemail=false&r=f2umh&utm_medium=email][Inside OPRO: Google DeepMind’s New Method that Optimizes Prompts Better than Humans]] #PromptEngineering
+ [[https://www.nature.com/articles/s44159-023-00241-5][Using large language models in psychology]] #psychology
+ [[https://huggingface.co/docs/transformers/main/en/tasks/prompting][LLM prompting guide]] #Prompting
+ [[https://arxiv.org/abs/2310.06825][Mistral 7B]] #LLM #Pablo #GuardRails
+ [[https://restofworld.org/2023/ai-image-stereotypes/][https://restofworld.org/2023/ai-image-stereotypes/]] #CIAIS #Bias
+ [[https://arxiv.org/abs/2309.07124][RAIN: Your Language Models Can Align Themselves without Finetuning]] #SelfAlignment #LLMs
+ [[https://www.sciencedirect.com/science/article/pii/S2352340923006650][ChatSubs: A dataset of dialogues in Spanish, Catalan, Basque and Galician extracted from movie subtitles for developing advanced conversational models]] #Datasets
+ [[https://miccai2023-reproducibility-tutorial.github.io/][Reproducibility]] #Reproducibility #Checklist
+ [[https://arxiv.org/abs/2303.05977][Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models]] #MedicalVQA #ProyectoIA
+ [[https://tsar-workshop.github.io/program/papers/espinosa-zaragoza-etal-2023-automatic.pdf][Automatic Text Simplification for People with Cognitive Disabilities: Resource Creation within the ClearText Project]] #LecturaFacil
+ [[https://arxiv.org/pdf/2310.03744.pdf][Improved Baselines with Visual Instruction Tuning]] #ProyectoIA
+ [[https://www.discapnet.es/vida-independiente/accesibilidad-de-comunicacion/lectura-facil][Lectura fácil]] #LecturaFacil #Mirari
+ [[https://arxiv.org/abs/2211.07624][Semantic Similarity Models for Depression Severity Estimation]] #PrevenIA
+ [[https://www.nature.com/articles/s41598-023-42384-8][Humans inherit artificial intelligence biases]] #Bias
+ [[https://hitz-zentroa.github.io/GoLLIE/][GoLLIE: Guideline-following Large Language Model for Information Extraction]] #InformationExtraction
+ [[https://docs.google.com/presentation/d/1v7T6ejrSo87ndGeGC7tt6zeq-cftu03WWw7WL8Jskug/edit#slide=id.p][Evaluating and Optimizing your RAG App]] #PrevenIA #RAG
+ [[https://developer.nvidia.com/blog/preventing-health-data-leaks-with-federated-learning-using-nvidia-flare/?mkt_tok=MTU2LU9GTi03NDIAAAGOoFx0OyiM1rBsWvytCA4cq3d4WsrQpNzmVlU_Q57BP8G8hN85gYDrDDzjwf0P92snOvXvXlQ2J_NpRMNswAu2lOlTUYr_YHsjuwqbiJ7vliO7dEbkjQ][Preventing Health Data Leaks with Federated Learning Using NVIDIA FLARE]] #FederatedLearning
+ [[https://developer.nvidia.com/blog/accelerated-vector-search-approximating-with-rapids-raft-ivf-flat/?mkt_tok=MTU2LU9GTi03NDIAAAGOoFx0Ojl6-4voujswneRKI4VEOectfY9Pmne-BJGLqWcA7XXxgVeKQshA4VLdy0uApAhHgvgnwHB6DWNubRWEMavU9C6dqya-vToR0rJNNRQVS085YA][Accelerated Vector Search: Approximating with RAPIDS RAFT IVF-Flat]] #VectorSearch #PrevenIA
+ [[https://link.springer.com/article/10.1007/s10579-023-09670-3][MarIA and BETO are sexist: evaluating gender bias in large language models for Spanish]] #Bias
+ [[https://optuna.readthedocs.io/en/stable/tutorial/index.html][OPTuna]] #HyperparamenterTuning
+ [[https://ceur-ws.org/Vol-3496/][Early detection of mental disorders risk in Spanish (MentalRiskES)]] #Proceedings #PrevenIA
+ [[http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/article/view/6550][LyricSIM: A novel dataset and benchmark for similarity detection in Spanish song lyrics]] #Corpus
+ [[http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/article/view/6548/3948][Catalan Parliamentary Plenary Session Transcriptions from 2015 to 2022. The ParlaMintCAT Corpus]] #Corpus
+ [[https://arxiv.org/abs/2309.17428][CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets]] #ProyectoIA #LiteratureReview 
+ [[https://www.youtube.com/watch?v=O8WYUJTX5iM][The Relationship Between Drone Flying Height and Pixel Size]] #Usue #Drones
+ [[https://ieeexplore.ieee.org/document/9854763/authors#authors][Deep Dirichlet Uncertainty for Unsupervised Out-of-Distribution Detection of Eye Fundus Photographs in Glaucoma Screening]] #OPTRetina #OOD
+ [[https://arxiv.org/abs/2307.02792v2][What Should Data Science Education Do with Large Language Models?]] #DataScience #Education #ChatGPT

** Septiembre 2023

+ [[https://www.sciencedirect.com/science/article/pii/S2666379123003646?via%3Dihub#mmc1][An artificial intelligence system for the whole process from diagnosis to treatment suggestion of ischemic retinal diseases]] #OPTRetina
+ [[https://www.tanishq.ai/blog/posts/ddpo.html][Reinforcement Learning for Diffusion Models from Scratch]] #ReinforcementLearning #DifussionModels
+ [[https://ig.ft.com/generative-ai/][Generative AI exists because of the transformer]] #Transformers #Explanation
+ [[https://github.com/ixa-ehu/antidote-casimedicos/tree/main][Antidote CasiMedicos Datasets]] #ProyectoIA
+ [[https://arxiv.org/abs/2306.03189][Easy-to-Read in Germany: A Survey on its Current State and Available Resources]] #LecturaFacil #Mirari
+ [[https://arxiv.org/pdf/2309.14052.pdf][Single Image Test-Time Adaptation for Segmentation]] #DomainAdaption
+ [[https://www.plenainclusion.org/publicaciones/buscador/?_sf_s=lectura%20f%C3%A1cil&sort_order=_sfm_fecha_publicacion+desc+date][Recursos lectura fácil]] #LecturaFacil #Mirari
+ [[https://daisy.org/activities/standards/daisy/daisy-3/][Daisy format]] #Accesibilidad #Mirari
+ [[http://www.sidar.org/recur/desdi/pau/directriceseuropeas%20para%20facilitar%20la%20lectura.pdf][El Camino Más Fácil]] #LecturaFacil #Mirari
+ [[https://www.ifla.org/wp-content/uploads/2019/05/assets/hq/publications/professional-report/120-es.pdf][Directrices para materiales de lectura fácil]] #LecturaFacil #Mirari
+ [[https://link.springer.com/chapter/10.1007/978-3-031-42280-5_12][Towards an Automatic Easy-to-Read Adaptation of Morphological Features in Spanish Texts]] #TextoClaro
+ [[https://dl.acm.org/doi/10.1145/3373625.3418006][EASIER system. Language resources for cognitive accessibility]] #LecturaFacil #Mirari
+ [[https://dl.acm.org/doi/10.1145/2738046][Making It Simplext: Implementation and Evaluation of a Text Simplification System for Spanish]] #LecturaFacil #Mirari
+ [[https://aclanthology.org/C12-1023.pdf][Can Spanish Be Simpler? LexSiS]] #LecturaFacil #Mirari
+ [[https://rua.ua.es/dspace/bitstream/10045/30664/1/PLN_51_23.pdf][DysWebxia: Textos m´as Accesibles para Personas con Dislexia]] #TextoClaro #Dislexia
+ [[https://arasaac.org/pictograms/search/sport%20events][Search Pictograms]] #Pictograms
+ [[https://planetafacil.plenainclusion.org/][Planeta fácil]] #LecturaFacil #Mirari
+ [[https://www.biorxiv.org/content/10.1101/2023.09.12.557460v1][BrainLM: A foundation model for brain activity recordings]] #FoundationalModel #Brain #CarmenVidaurre
+ [[https://pytorch.org/blog/inside-the-matrix/?utm_content=265147245&utm_medium=social&utm_source=twitter&hss_channel=tw-776585502606721024][Inside the Matrix: Visualizing Matrix Multiplication, Attention and Beyond]] #Visualisations
+ [[https://supervisely.com/blog/lessons-learned-from-training-a-segmentation-model-on-synthetic-data/][Lessons Learned From Training a Segmentation Model On Synthetic Data]] #Segmentation #SyntheticData
+ [[https://www.youtube.com/watch?v=jkrNMKz9pWU][A Hackers' Guide to Language Models]] #LLM #FastAI
+ [[https://huggingface.co/blog/gaussian-splatting][Introduction to 3D Gaussian Splatting]] #Graphics
+ [[https://huggingface.co/blog/optimize-llm][Optimizing your LLM in production]] #Optimizations #PrevenIA
+ [[https://www.sciencedirect.com/science/article/pii/S0885230823000864][Towards inclusive automatic speech recognition]] #SpeechRecognition #Mirari
+ [[https://gpt-index.readthedocs.io/en/latest/examples/embeddings/huggingface.html#optimumembedding][Optimum]] #Embeddings #PrevenIA
+ [[http://ai.stanford.edu/blog/retrieval-based-NLP/][Building Scalable, Explainable, and Adaptive NLP Models with Retrieval]] #InformationRetrieval #Prevenia
+ [[https://github.com/primeqa/primeqa][PrimeQA]] #InformationRetrieval #PrevenIA
+ [[https://www.researchgate.net/publication/370215194_Artificial_Intelligence_for_Sign_Language_Translation_-A_Design_Science_Research_Study][Artificial Intelligence for Sign Language Translation -A Design Science Research Study]] #LenguaSignos
+ [[https://www.sciencedirect.com/science/article/pii/S0957417422020115#b66][A survey on Sign Language machine translation]] #LenguaSignos
+ [[https://dl.acm.org/doi/pdf/10.1145/3600211.3604681][AI Art and its Impact on Artists]] #CIAIS #Ethics
+ [[https://arxiv.org/abs/2309.03516][Topological fingerprints for audio identification]] #TDA
+ [[https://www.microsoft.com/en-us/research/blog/frontiers-of-multimodal-learning-a-responsible-ai-approach/][Frontiers of multimodal learning: A responsible AI approach]] #MultiModal #Biases
+ [[https://arxiv.org/abs/2211.05776][High-Quality Entity Segmentation]] #Segmentation
+ [[https://arxiv.org/abs/2309.05519][NExT-GPT: Any-to-Any Multimodal LLM]] #MultiModal
+ [[https://dienhoa.github.io/dhblog/posts/finetune_clip.html][Why and How to Fine-tune CLIP]] #FineTuning
+ [[https://twitter.com/katieelink/status/1702331358742487402?s=20][Biomedical Computer Vision models]] #MedicalAI
+ [[https://www.inclusion-europe.eu/easy-to-read-standards-guidelines/][Information for all: European standards for making information easy to read and understand]] #Accesibilidad #Mirari
+ [[https://huggingface.co/spaces/coqui/xtts][Coqui🐸 XTTS]] #Text2Speech #VoiceCloning
+ [[https://www.nature.com/articles/s41586-023-05881-4][Foundation models for generalist medical artificial intelligence]]  #ProyectoIA #MultiModal
+ [[https://arxiv.org/pdf/2308.02463.pdf][Towards Generalist Foundation Model for Radiology]]  #ProyectoIA #MultiModal
+ [[https://arxiv.org/abs/2306.07831][Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Images]] #ProyectoIA #MultiModal
+ [[https://www.medrxiv.org/content/10.1101/2023.06.07.23291119v1][Fostering transparent medical image AI via an image-text foundation model grounded in medical literature]] #ProyectoIA #MultiModal
+ [[https://arxiv.org/abs/2008.06775][Model Patching: Closing the Subgroup Performance Gap with Data Augmentation]] #DataAuditing #Ruben
+ [[https://www.nature.com/articles/s41591-023-02504-3.epdf?sharing_token=2umlCrKLgEIF8vmuLpQ7AtRgN0jAjWel9jnR3ZoTv0NWSxjlTuWM3jUBxiqED7ai3ueIDYQ_xX2BBBGXn0IDY_RMdGid_ppbXRxR40prhjrWvtzO3o_QB1gW6NTYt8EB0UO5VjWecg4rWh3LM_L-Rf59L6s9Fx7yR521Lp3GfhU%3D][A visual–language foundation model for pathology image analysis using medical Twitter]] #ProyectoIA #MultiModal
+ [[https://arxiv.org/abs/2308.15670][Multimodal Foundation Models For Echocardiogram Interpretation]] #ProyectoIA #MultiModal
+ [[https://www.nature.com/articles/s41586-023-06555-x][A foundation model for generalizable disease detection from retinal images]] #OPTRetina #SelfSupervisedLearning [[https://github.com/rmaphoh/RETFound_MAE][Code]]
+ [[https://facebookresearch.github.io/nougat/][Nougat: Neural Optical Understanding for Academic Documents]] #OCR
+ [[https://arxiv.org/abs/2308.06259][Self-Alignment with Instruction Backtranslation]] #SemiSupervisedLearning
+ [[https://arxiv.org/abs/2308.15670v2][Multimodal Foundation Models For Echocardiogram Interpretation]] #MultiModal #Medicine #ProyectoIA
+ [[https://www.cambridge.org/core/journals/natural-language-engineering/article/abs/designing-a-virtual-patient-dialogue-system-based-on-terminologyrich-resources-challenges-and-evaluation/CFCEE7294A86F77C0AD0E4F18D43E72A][Designing a Virtual Patient Dialogue System Based on Terminology-rich Resources: Challenges and Evaluation]] #PrevenIA #Evaluación
+ [[https://ceur-ws.org/Vol-2936/paper-11.pdf][Overview of BioASQ 2021-MESINESP track. Evaluation of advance hierarchical classification techniques for scientific literature, patents and clinical trials]] #MedicalDocuments #Database #ProyectoIA
+ [[https://developer.nvidia.com/blog/accelerating-vector-search-using-gpu-powered-indexes-with-rapids-raft/?ncid=so-nvsh-979215-vt27][Accelerating Vector Search: Using GPU-Powered Indexes with RAPIDS RAFT]] #VectorSearch #PrevenIA
+ [[https://arxiv.org/abs/2309.05542][Kani: A Lightweight and Highly Hackable Framework for Building Language Model Applications]] #PrevenIA #ProyectoIA #Tools
+ [[https://arxiv.org/abs/2106.11520][BARTScore: Evaluating Generated Text as Text Generation]] #CLARAMed
+ [[https://blog.langchain.dev/syncing-data-sources-to-vector-stores/][Syncing data sources to vector stores]] #PrevenIA
+ [[https://www.fast.ai/posts/2023-09-04-learning-jumps/][Can LLMs learn from a single example?]] #LLM
+ [[https://huggingface.co/blog/falcon-180b][Spread Your Wings: Falcon 180B is here]] #LLM
+ [[https://haystack.deepset.ai/blog/talk-to-haystack-docs][Talk to Haystack Docs: Creating a Domain-Focused Q&A RAG Pipeline with WebRetriever]] #ProyectoIA #Retriever
+ [[https://github.com/facebookresearch/muss][Multilingual Unsupervised Sentence Simplification]] #TextSimplfication #CLARAMED
+ [[https://medinform.jmir.org/2022/11/e38095#ref17][Medical Text Simplification Using Reinforcement Learning (TESLEA): Deep Learning–Based Text Simplification Approach]] #TextSimplification #CLARAMED #ReinforcementLearning
+ [[https://github.com/asahi417/lm-question-generation][Question and Answer Generation with Language Models]] #PrevenIA #QuestionAnsweringGeneration
+ [[https://arxiv.org/abs/1905.02851][FAQ Retrieval using Query-Question Similarity and BERT-Based Query-Answer Relevance]] #FAQRetrieval #PrevenIA
+ [[https://openai.com/blog/teaching-with-ai][Educator FAQ ChatGPT]] #Education #ChatGPT
+ [[https://www.sciencedirect.com/science/article/pii/S0957417421016158][Preprocessing of normative documents for interactive question answering]]  #PrevenIA #DatasetGeneration
+ [[https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-022-04751-6][CoQUAD: a COVID-19 question answering dataset system, facilitating research, benchmarking, and practice]] #PrevenIA #DatasetGeneration
+ [[https://link.springer.com/chapter/10.1007/978-3-031-42536-3_16][A Multimodal Dataset to Create Manufacturing Digital Twins]] #Dataset
+ [[https://arxiv.org/abs/2211.10154][CRAFT: Concept Recursive Activation FacTorization for Explainability]] #Explainability #ComputerVision #Master
+ [[https://arxiv.org/abs/2309.00087][Large language models in medicine: the potentials and pitfalls]] #ProyectoIA #Medicine #LLM
+ [[https://arxiv.org/abs/2308.12966][Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities]] #ProyectoIA #MultiModal
+ [[https://arxiv.org/abs/2307.13528v2][FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios]] #LLM #Factuality
+ [[https://arxiv.org/abs/2308.09687v2][Graph of Thoughts: Solving Elaborate Problems with Large Language Models]] #LLMs #Prompting
+ [[https://arxiv.org/abs/2308.15930][LLaSM: Large Language and Speech Model]] #Speech
+ [[https://arxiv.org/pdf/2308.16184v1.pdf][SAM-Med2D]] #Segmentation #Ruben

** Agosto 2023

+ [[https://arxiv.org/abs/2305.12031v2][Clinical Camel: An Open Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding]] #MedicalLLM #ProyectoIA
+ [[https://huggingface.co/blog/dpo-trl][Fine-tune Llama 2 with DPO]] #ReinforcementLearning #PrevenIA #ProyectoIA
+ [[https://ai.meta.com/blog/dinov2-facet-computer-vision-fairness-evaluation/?utm_source=twitter&utm_medium=organic_social&utm_campaign=blog&utm_content=video][Evaluating the fairness of computer vision models]] #ComputerVision
+ [[https://saco.csic.es/index.php/s/sCS9BbLNyRZzbWB][Bibliografía CLARA-MeD]] #CLARAMed
+ [[https://spj.science.org/doi/10.34133/plantphenomics.0073][Deep Learning Enables Instant and Versatile Estimation of Rice Yield Using Ground-Based RGB Images]] #PlantPhenomics #Usue
+ [[https://escuelapacientes.riojasalud.es/][Escuela de Pacientes]] #PrevenIA #ProyectoIA
+ [[https://acl2023-retrieval-lm.github.io/][Retrieval-based Language Models and Applications]] #ProyectoIA #PrevenIA
+ [[https://precisionhealthllm.github.io/][Precision Health in the Age of LLMs]] #ProyectoIA
+ [[https://www.kaggle.com/code/gusthema/asl-fingerspelling-recognition-w-tensorflow/notebook][ASL Fingerspelling Recognition w/ TensorFlow]] #LenguaSignos
+ [[https://github.com/huggingface/trl][TRL - Transformer Reinforcement Learning]] #ProyectoIA #CLARAMed
+ [[https://www.kaggle.com/code/jhoward/getting-started-with-llms][Getting Started With LLMs]] #LLMs #Prompting #FastAI
+ [[https://github.com/McGill-NLP/instruct-qa][Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering]] #PrevenIA #ProyectoIA #QuestionAnswering
+ [[https://github.com/langchain-ai/langsmith-cookbook/blob/main/testing-examples/qa-correctness/qa-correctness.ipynb][Q&A System Correctness]] #QuestionAnswering #PrevenIA 
+ [[https://github.com/NVlabs/neuralangelo][Neuralangelo: High-Fidelity Neural Surface Reconstruction]] #3DReconstruction
+ [[https://www.iic.uam.es/noticias/lanzamos-nueva-version-modelo-lenguaje-rigoberta-2/][Lanzamos una nueva versión del modelo de lenguaje del IIC: RigoBERTa 2]] #LLM #Spanish #Encoderonly
+ [[https://medium.com/@vered1986/tips-for-writing-nlp-papers-9c729a2f9e1f][Tips for Writing NLP Papers]] #PhD #Tips
+ [[https://arxiv.org/abs/2308.04948][Extrapolating Large Language Models to Non-English by Aligning Languages]] #LLMs #Multilingual
+ [[https://helenajamborwrites.netlify.app/posts/image_cheatsheets/][CHEAT SHEETS FOR IMAGE PUBLISHING]] #ImagePublishing #PhD 
+ [[https://www.youtube.com/watch?v=OHZHM8hcyI4][BARK: Free Text to Speech & Voice Cloning]] #Text2Speech #Mirari
+ [[https://ai.meta.com/blog/seamless-m4t/][a foundational multimodal model for speech translation]] #speech2text #text2speech #Mirari
+ [[https://arxiv.org/abs/2307.16789][ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs]] #ProyectoIA 
+ [[https://link.springer.com/article/10.1007/s13748-023-00304-x?utm_source=toc&utm_medium=email&utm_campaign=toc_13748_12_3&utm_content=etoc_springer_20230811][An automated classification framework for glaucoma detection in fundus images using ensemble of dynamic selection methods]] #Glaucoma #OPTRetina
+ [[https://arxiv.org/abs/2308.05374][Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment]] #LLM #ProyectoIA #Evaluation
+ [[https://blog.langchain.dev/evaluating-rag-pipelines-with-ragas-langsmith/][Evaluating RAG pipelines with Ragas + LangSmith]] #QuestionAnswering #ProyectoIA #PrevenIA
+ [[https://huggingface.co/blog/idefics][OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents]] #MultiModal #ProyectoIA
+ [[https://jamanetwork.com/journals/jamanetworkopen/fullarticle/2808557?utm_source=substack&utm_medium=email][Comparison of Ophthalmologist and Large Language Model Chatbot Responses to Online Patient Eye Care Questions]] #ProyectoIA
+ [[https://clibrain.com/blog/llama-2-13b-pr?utm_source=twitter&utm_medium=feed&utm_campaign=llama-2-13b][Adaptación de Llama 2 13B de Meta para un mejor rendimiento en espyearl]] #LLMs #PrevenIA
+ [[https://huyenchip.com/2023/08/16/llm-research-open-challenges.html][Open challenges in LLM research]] #LLMs
+ [[https://twitter.com/DotCSV/status/1691770359681294638?s=20][WhisperX]] #Speech2Text #Mirari
+ [[https://www.deeplearning.ai/short-courses/large-language-models-semantic-search/][Large Language Models with Semantic Search]] #SemanticSearch #PrevenIA #Course
+ [[https://arxiv.org/abs/2307.16877][Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering]] #ProyectoIA #Evaluación
+ [[https://arxiv.org/abs/2308.01320][DeepSpeed-Chat: Easy, Fast and Affordable RLHF Training of ChatGPT-like Models at All Scales]] #ReinforcementLearning
+ [[https://medlineplus.gov/spanish/all_easytoread.html][Documentos de lectura fácil medline]] #ProyectoIA #LecturaFacil 
+ [[https://paperswithcode.com/dataset/pathvqa][PathVQA]] #ProyectoIA #Dataset #VisualQuestionAnswering
+ [[https://www.nejm.org/doi/full/10.1056/NEJMsr2214184][Benefits, Limits, and Risks of GPT-4 as an AI Chatbot for Medicine]] #ProyectoIA #QuestionAnswering #Biomedical 
+ [[https://arxiv.org/pdf/2307.14334.pdf][Towards Generalist Biomedical AI]] #ProyectoIA #VisualQuestionAnswering #Biomedical #MultiModal
+ [[https://arxiv.org/abs/2307.05131][Overview of BioASQ 2023: The eleventh BioASQ challenge on Large-Scale Biomedical Semantic Indexing and Question Answering]] #ProyectoIA #QuestionAnswering #Biomedical
+ [[https://arxiv.org/pdf/2102.05281.pdf][Biomedical Question Answering: A Survey of Approaches and Challenges]] #ProyectoIA #QuestionAnswering #Biomedical
+ [[https://www.nature.com/articles/s41597-023-02068-4][BioASQ-QA: A manually curated corpus for Biomedical Question Answering]] #ProyectoIA  #QuestionAnswering #Biomedical
+ [[https://link.springer.com/chapter/10.1007/978-3-030-11680-4_1][Clinical, Consumer Health, and Visual Question Answering]] #ProyectoIA  #VisualQuestionAnswering #Biomedical #MultiModal
+ [[https://arxiv.org/pdf/2102.05281.pdf][Biomedical Question Answering: A Survey of Approaches and Challenges]] #ProyectoIA  #QuestionAnswering #Biomedical #MultiModal
+ [[https://arxiv.org/abs/2303.00534][RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training]] #ProyectoIA #VisualQuestionAnswering #Biomedical #MultiModal #InformationRetrieval
+ [[https://arxiv.org/abs/2307.15189][Med-Flamingo: a Multimodal Medical Few-shot Learner]] #ProyectoIA #VisualQuestionAnswering #Biomedical #MultiModal
+ [[https://zenodo.org/record/5513237][Spanish Biomedical Crawled Corpus]] #ProyectoIA #Dataset
+ [[https://pubmed.ncbi.nlm.nih.gov/31438331/][Design and Evaluation of an Automatic Speech Recognition Model for Clinical Notes in Spanish in a Mobile Online Environment]] #ProyectoIA #SpeechRecognition
+ [[https://pubmed.ncbi.nlm.nih.gov/31438331/][Automatic Speech Recognition Model Adaptation to Medical Domain Using Untranscribed Audio]] #ProyectoIA #SpeechRecognition
+ [[https://arxiv.org/abs/2303.00091][Improving Medical Speech-to-Text Accuracy with Vision-Language Pre-training Model]] #ProyectoIA #SpeechRecognition
+ [[https://arxiv.org/abs/2303.17580][HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face]] #ProyectoIA #Agents
+ [[https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10292051/#REF19][Embracing Large Language Models for Medical Applications: Opportunities and Challenges]] #ProyectoIA #Biomedical
+ [[https://arxiv.org/abs/2304.14204][Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining]] #ProyectoIA #VisualQuestionAnswering #Biomedical #MultiModal
+ [[https://link.springer.com/chapter/10.1007/978-3-030-32251-9_57][Overcoming Data Limitation in Medical Visual Question Answering]] #ProyectoIA #VisualQuestionAnswering #Biomedical
+ [[https://dl.acm.org/doi/10.1561/1500000019][The Probabilistic Relevance Framework: BM25 and Beyond]] #ProyectoIA #InformationRetrieval
+ [[https://ai.meta.com/blog/retrieval-augmented-generation-streamlining-the-creation-of-intelligent-natural-language-processing-models/][Retrieval Augmented Generation: Streamlining the creation of intelligent natural language processing models]] #ProyectoIA #InformationRetrieval
+ [[https://huggingface.co/blog/ray-rag][Retrieval Augmented Generation with Huggingface Transformers and Ray]] #ProyectoIA #InformationRetrieval
+ [[https://ai.nejm.org/doi/full/10.1056/AIoa2300068][Almanac: Retrieval-Augmented Language Models for Clinical Medicine]] #ProyectoIA #InformationRetrieval #VisualQuestionAnswering #Biomedical
+ [[https://arxiv.org/abs/2002.08909][REALM: Retrieval-Augmented Language Model Pre-Training]] #ProyectoIA #InformationRetrieval
+ [[https://link.springer.com/article/10.1007/s11227-022-04474-8][Hybrid deep learning model for answering visual medical questions]] #ProyectoIA  #VisualQuestionAnswering #Biomedical
+ [[https://ieeexplore.ieee.org/abstract/document/10082873][Enhancing Biomedical ReQA With Adversarial Hard In-Batch Negative Samples]] #ProyectoIA #InformationRetrieval #QuestionAnswering #Biomedical
+ [[https://arxiv.org/pdf/2212.13138.pdf][Large Language Models Encode Clinical Knowledge]] #ProyectoIA #QuestionAnswering #Biomedical
+ [[https://arxiv.org/pdf/2306.00890v1.pdf][LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day]] #ProyectoIA #VisualQuestionAnswering #Biomedical
+ [[https://arxiv.org/abs/2304.08247][MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data]] #ProyectoIA #QuestionAnswering #Biomedical
+ [[https://arxiv.org/abs/2306.12174][OphGLM: Training an Ophthalmology Large Language-and-Vision Assistant based on Instructions and Dialogue]] #ProyectoIA #VisualQuestionAnswering #Biomedical
+ [[https://arxiv.org/abs/2307.07518][CephGPT-4: An Interactive Multimodal Cephalometric Measurement and Diagnostic System with Visual Large Language Model]] #ProyectoIA #VisualQuestionAnswering #Biomedical
+ [[https://blog.allenai.org/vanilla-vqa-adcaaaa94336][Vanilla VQA]] #ProyectoIA  #VisualQuestionAnswering 
+ [[https://arxiv.org/abs/2307.16184][Unified Model for Image, Video, Audio and Language Tasks]] #ProyectoIA #MultiModal
+ [[https://ai.googleblog.com/2023/08/multimodal-medical-ai.html?linkId=8927847&m=1][Multimodal medical AI]] #ProyectoIA  #QuestionAnswering #Biomedical #MultiModal
+ [[https://lilianweng.github.io/posts/2020-10-29-odqa/][How to Build an Open-Domain Question Answering System?]] #ProyectoIA  #QuestionAnswering #Biomedical
+ [[https://arxiv.org/abs/2305.14458][Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSA]] #ProyectoIA #TextSimplification #ClaraMed
+ [[https://arxiv.org/abs/2305.12532][Multilingual Simplification of Medical Texts]] #ProyectoIA #TextSimplification #CLaraMed
+ [[https://academic.oup.com/bioinformatics/article/27/14/2025/195171][Question answering systems in biology and medicine—the time is now]] #ProyectoIA #QuestionAnswering #Biomedical
+ [[https://dl.acm.org/doi/10.1162/coli_a_00368][The Design and Implementation of XiaoIce, an Empathetic Social Chatbot]] #ProyectoIA #QuestionAnswering #Biomedical
+ [[https://link.springer.com/article/10.1007/s00521-021-06748-3#citeas][Recent progress in leveraging deep learning methods for question answering]] #ProyectoIA #QuestionAnswering #Biomedical
+ [[https://arxiv.org/pdf/2305.09617.pdf][Towards Expert-Level Medical Question Answering with Large Language Models]] #ProyectoIA #QuestionAnswering #Biomedical
+ [[https://sites.research.google/med-palm/][Med-PaLM]] #ProyectoIA #MultiModal #QuestionAnswering #VisualQuestionAnsering #Biomedical
+ [[https://chqa.nlm.nih.gov/][CHiQA]] #ProyectoIA #QuestionAnswering #Biomedical
+ [[https://arxiv.org/abs/2306.02022][ACI-BENCH: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation]] #ProyectoIA #ClinicalNotes
+ [[https://arxiv.org/abs/2305.17364][An Investigation of Evaluation Metrics for Automated Medical Note Generation]] #ProyectoIA #ClinicalNotes
+ [[https://link.springer.com/book/10.1007/978-3-319-78503-5][Clinical Text Mining]] #ProyectoIA #ClinicalNotes
+ [[https://zenodo.org/record/4279041#.Y_uCZh_MI2w][Dataset for Automated Medical Transcription]] #ProyectoIA #ClinicalNotes




** Julio 2023

+ [[https://huggingface.co/blog/os-llms][Open-Source Text Generation & LLM Ecosystem at Hugging Face]] #LLMs 
+ [[https://huggingface.co/blog/mms_adapters][Fine-tuning MMS Adapter Models for Multi-Lingual ASR]] #ASR #Mirari
+ [[https://huggingface.co/blog/bridgetower][Accelerating Vision-Language Models: BridgeTower on Habana Gaudi2]] #ProyectoIA 
+ [[https://huggingface.co/blog/llama2][Llama 2 is here - get it on Hugging Face]] #LLMs #PrevenIA
+ [[https://pyimagesearch.com/2023/06/19/fundamentals-of-recommendation-systems/?utm_source=Drip&utm_medium=Email&utm_campaign=WeeklyUpdate&utm_content=19June2023NonUnivLink1EnrollInPyImageSearchUniversity][Fundamentals of Recommendation Systems]] #RecommendationSystems
+ [[https://editing-images-project.hf.space/index.html][LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance]] #ImageEditing #Difusion
+ [[https://arxiv.org/abs/2306.16410][Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language]] #Imagecaptioning
+ [[https://t.co/5SJfuQVQxN][Using AI to Implement Effective Teaching Strategies in Classrooms: Five Strategies, Including Prompts]] #Teaching #ChatGPT

** Junio 2023

+ [[https://montoliu.naukas.com/2021/11/14/daltonismo-la-solucion-esta-en-el-morado-y-el-naranja/][Daltonismo: la solución está en el morado y el naranja]] #Accesibilidad #Mirari
+ [[https://deepmind-tapir.github.io/][TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement]] #Tracking
+ [[https://ai.facebook.com/blog/voicebox-generative-ai-model-speech/][Introducing Voicebox: The first generative AI model for speech to generalize across tasks with state-of-the-art performance]] #VoicenGeneration #Mirari
+ [[https://www.amazon.science/publications/web-scale-semantic-product-search-with-large-language-models][Web-scale semantic product search with large language models]] #SemanticSearch
+ [[https://arxiv.org/abs/2306.01744][Disproving XAI Myths with Formal Methods -- Initial Results]] #Interpretability
+ [[https://microsoft.github.io/AI-For-Beginners/?id=getting-started][Artificial Intelligence for Beginners - A Curriculum]] #InteligenciaArtificial #Curso
+ [[https://arxiv.org/abs/2306.06672][Reducing Barriers to Self-Supervised Learning: HuBERT Pre-training with Academic Compute]] #Audio
+ [[https://arxiv.org/abs/2301.08243][Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture]] #Pretraining #ImageClassification
+ [[https://arxiv.org/abs/2306.02022][ACI-BENCH: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation]] #HistoriaClinica #AnaRosa
+ [[https://arxiv.org/abs/2305.17364][An Investigation of Evaluation Metrics for Automated Medical Note Generation]] #Metrics #HistoriaClinica #AnaRosa
+ [[https://huggingface.co/learn/audio-course][Audio course]] #HuggingFace #Audio #Mirari
+ [[https://forum.image.sc/t/introducing-the-java-deep-learning-library-jdll/82255][Introducing the Java Deep Learning Library - JDLL]] #ImageJ #Adrian
+ [[https://jamanetwork.com/journals/jamaophthalmology/fullarticle/2805759?guestAccessKey=eb14c3f5-b0be-4d44-9327-961db4bd3f00&utm_source=silverchair&utm_medium=email&utm_campaign=article_alert-jamaophthalmology&utm_content=olf&utm_term=060823][Accuracy of Artificial Intelligence in Estimating Best-Corrected Visual Acuity From Fundus Photographs in Eyes With Diabetic Macular Edema]] #UPRetina
+ [[https://huggingface.co/blog/falcon][The Falcon has landed in the Hugging Face ecosystem]] #LLMs
+ [[https://arxiv.org/abs/2306.00890][LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day]] #ChatBot #Biomedicine 
+ [[https://arxiv.org/pdf/2303.15647.pdf][Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning]] #FineTuning
+ [[https://www.cloudskillsboost.google/course_sessions/3200330/quizzes/379209][Create Image Captioning Models]] #Gobierno #ImageCaptioning
+ [[https://link.springer.com/article/10.1007/s10209-021-00823-1][Machine translation from text to sign language: a systematic review]] #LenguaSignos

** Mayo 2023

+ [[https://twitter.com/EdenEmarco177/status/1664590786137137158][Summarization LangChain]] #Summarization #PrevenIA
+ [[https://www.fast.ai/posts/2023-05-31-extinction.html][Is Avoiding Extinction from AI Really an Urgent Priority?]] #CIAIS
+ [[https://blog.google/technology/health/5-myths-about-medical-ai-debunked/?linkId=8780071][5 myths about medical AI, debunked]] #UPRetina
+ [[https://www.pinecone.io/learn/langchain/][LangChain AI Handbook]] #ChatBot #LangChain #PrevenIA
+ [[https://huggingface.co/blog/4bit-transformers-bitsandbytes][Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA]] #Quantization #PrevenIA
+ [[https://huggingface.co/blog/fl-with-flower][Federated Learning using Hugging Face and Flower]] #FederatedLearning
+ [[http://sltat.cs.depaul.edu/sltat_2023.htm][Eighth International Workshop on Sign Language Translation and Avatar Technology]] #LenguaSignos #Congreso
+ [[https://slrtp-2022.github.io/][Sign Language Recognition, Translation & Production]] #LenguaSignos #Congreso
+ [[https://signon-project.eu/][The SignON Project]] #LenguaSignos 
+ [[https://arxiv.org/pdf/2305.11206.pdf][LIMA: Less Is More for Alignment]] #LLMs
+ [[https://ai.facebook.com/blog/multilingual-model-speech-recognition/?utm_source=twitter&utm_medium=organic_social&utm_campaign=blog&utm_content=card][Introducing speech-to-text, text-to-speech, and more for 1,100+ languages]] #Speech2Text #Text2Speech
+ [[https://arxiv.org/abs/2204.05044][From Modern CNNs to Vision Transformers: Assessing the Performance, Robustness, and Classification Strategies of Deep Learning Models in Histopathologyhttps://arxiv.org/abs/2204.05044]] #ImageClasssification #DomainShift #Robustness
+ [[https://arxiv.org/abs/2305.07804][Dr. LLaMA: Improving Small Language Models on PubMedQA via Generative Data Augmentation]] #QuestionAnswering
+ [[https://towardsdatascience.com/hugging-face-transformers-agent-3a01cf3669ac][Hugging Face Transformers Agent]] #Agents
+ [[https://arxiv.org/abs/2305.06500][InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning]] #VisualQuestionAnswering
+ [[https://arxiv.org/abs/2305.11738][CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing]] #LLMs
+ [[https://news.utexas.edu/2023/05/01/brain-activity-decoder-can-reveal-stories-in-peoples-minds/][Brain Activity Decoder Can Reveal Stories in People’s Minds]] #Neuro
+ [[https://sambanova.ai/blog/introducing-bloomchat-176b-the-multilingual-chat-based-llm/][BLOOMChat: a New Open Multilingual Chat LLM]] #LLMs #ChatBot #PrevenIA
+ [[https://rachel.fast.ai/posts/2023-05-16-ai-centralizes-power/][AI and Power: The Ethical Challenges of Automation, Centralization, and Scale]] #Ethics #CIAIS
+ [[https://huggingface.co/blog/assisted-generation][Assisted Generation: a new direction toward low-latency text generation]]  #LLMs #Optimization #Inference
+ [[https://huggingface.co/blog/chatbot-amd-gpu][Run a Chatgpt-like Chatbot on a Single GPU with ROCm]] #LLMs #Optimization
+ [[https://huggingface.co/blog/rwkv][Introducing RWKV - An RNN with the advantages of a transformer]] #LLMs #RNN
+ [[https://technomancers.ai/eu-ai-act-to-target-us-open-source-software/#more-561][EU AI Act To Target US Open Source Software]] #CIAIS
+ [[https://engineering.fb.com/2017/03/29/data-infrastructure/faiss-a-library-for-efficient-similarity-search/][Faiss: A library for efficient similarity search]] #PrevenIA #InformationRetrieval #FAISS
+ [[https://huggingface.co/docs/datasets/v1.0.1/faiss_and_ea.html][Adding a FAISS or Elastic Search index to a Dataset]] #PrevenIA #InformationRetrieval #FAISS #HuggingFace
+ [[https://towardsdatascience.com/understanding-dense-passage-retrieval-dpr-system-bce5aee4fd40][Understanding Dense Passage Retrieval (DPR) System]] #PrevenIA #InformationRetrieval
+ [[https://arxiv.org/abs/2305.06300][Evaluating Embedding APIs for Information Retrieval]] #PrevenIA #InformationRetrieval
+ [[https://sites.google.com/ecolint.ch/aiineducation/resources/teaching-resources?authuser=0][AI in Education]] #Education
+ [[https://huggingface.co/blog/text-to-video][Text-to-Video: The Task, Challenges and the Current State]] #Text2Video
+ [[https://huggingface.co/blog/starcoder][StarCoder: A State-of-the-Art LLM for Code]] #LLMs #Coding
+ [[https://arxiv.org/abs/2305.05665][ImageBind: One Embedding Space To Bind Them All]] #MultiModality
+ [[https://www.mlexpert.io/machine-learning/tutorials/alpaca-fine-tuning][Fine-tuning Alpaca and LLaMA: Training on a Custom Dataset]] #FineTuning #LLMs #ClaraMed
+ [[https://learnprompting.org/docs/intro][Learn Prompting]] #Prompting #LLMs
+ [[https://github.com/NielsRogge/Transformers-Tutorials/tree/master][Transformers-Tutorials]] #Tutorials #Transformers
+ [[https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/ViLT/Inference_with_ViLT_(visual_question_answering).ipynb][Performing visual question answering (VQA) with ViLT]] #VisualQuestionAnswering #Gobierno
+ [[https://arxiv.org/abs/2202.13876][PMC-Patients: A Large-scale Dataset of Patient Summaries and Relations for Benchmarking Retrieval-based Clinical Decision Support Systems]] #HistoriaClinica #AnaRosa
+ [[https://arxiv.org/abs/2305.03433][Towards Applying Powerful Large AI Models in Classroom Teaching: Opportunities, Challenges and Prospects]] #Teaching #ChatGPT
+ [[https://huyenchip.com/2023/05/02/rlhf.html][RLHF: Reinforcement Learning from Human Feedback]] #RLHF #ChatGPT
+ [[https://aclanthology.org/2023.findings-eacl.27/][Gauging the Gap Between Human and Machine Text Simplification Through Analytical Evaluation of Simplification Strategies and Errors]] #ClaraMed #QualitativeEvaluation
+ [[https://leo.andeol.eu/publication/andeol-2021-learning/][Learning Domain Invariant Representations by Joint Wasserstein Distance Minimization]] #SemiSupervisedLearning #CarmenVidaurre #DomainShift
+ [[https://speakerdeck.com/gpeyre/the-mathematics-of-neural-networks][The Mathematics of Neural Networks]]
+ [[https://www.assemblyai.com/blog/the-full-story-of-large-language-models-and-rlhf/][The Full Story of Large Language Models and RLHF]] #LLMs #CursoPDI
+ [[https://towardsdatascience.com/nlp-with-python-knowledge-graph-12b93146a458][NLP with Python: Knowledge Graph]] #KnowledgeGraph #M&M
+ [[https://www.fast.ai/posts/2023-05-03-mojo-launch.html][Mojo may be the biggest programming language advance in decades]] #Mojo #Parallelization
+ [[https://huggingface.co/transformers/v4.9.2/performance.html][Performance and Scalability: How To Fit a Bigger Model and Train It Faster]] #LLMs #BigModels
+ [[https://www.mlexpert.io/machine-learning/tutorials/alpaca-fine-tuning][Fine-tuning Alpaca and LLaMA: Training on a Custom Dataset]] #CLARA-Med #Fine-Tuning #LLMs #BigModels
+ [[https://seeai.hashnode.dev/how-to-create-an-app-that-answers-questions-about-your-contract-using-embeddings-and-gpt][How to Create an App that Answers Questions About Your Contract Using Embeddings and GPT]] #PrevenIA

** Abril 2023

+ [[https://arxiv.org/abs/2304.11968][Track Anything: Segment Anything Meets Videos]] #Tracking
+ [[https://dl.acm.org/doi/10.1145/3544549.3585679][THERIF: Themes for Readability from Iterative Feedback]] #Readability
+ [[https://dl.acm.org/doi/10.1145/3544548.3581367][Digital Reading Rulers]] #Readability
+ [[https://github.com/freedmand/semantra][Semantra]] #SemanticSearch #PrevenIA
+ [[https://gradio.app/gradio-and-llm-agents/][Gradio & LLM Agents]] #LLMs #LangChain
+ [[https://arxiv.org/abs/2304.11062][Scaling Transformer to 1M tokens and beyond with RMT]] #Transformers
+ [[https://www.crowdcast.io/c/rh66hcwivly0][LangChain Document Question-Answering Webinar]] #PrevenIA
+ [[https://www.databricks.com/blog/2023/04/12/dolly-first-open-commercially-viable-instruction-tuned-llm?utm_source=substack&utm_medium=email][Free Dolly: Introducing the World's First Truly Open Instruction-Tuned LLM]] #LLM #PrevenIA
+ [[https://python.langchain.com/en/latest/use_cases/evaluation/qa_generation.html][https://python.langchain.com/en/latest/use_cases/evaluation/qa_generation.html]] #QuestionAnswering
+ [[https://www.mikulskibartosz.name/alternatives-to-open-ai-gpt-using-open-source-models-with-langchain/][Alternatives to OpenAI GPT model: using an open-source Cerebras model with LangChain]] #PrevenIA
+ [[https://blog.vespa.ai/improving-zero-shot-ranking-with-vespa-part-two/][Improving Zero-Shot Ranking with Vespa Hybrid Search - part two]] #SemanticSearch
+ [[https://www.promptingguide.ai/][Prompt Engineering Guide]] #PromptEngineering
+ [[https://blog.futuresmart.ai/semantic-search-using-llamaindex-and-langchain][Semantic Search using LlamaIndex and Langchain]] #Prevenia #SemanticSearch
+ [[https://ai.facebook.com/blog/dino-v2-computer-vision-self-supervised-learning/][DINOv2: State-of-the-art computer vision models with self-supervised learning]] #SelfSupervisedLearning
+ [[https://theconversation.com/la-dificultad-de-entender-el-lenguaje-que-utilizan-las-administraciones-publicas-203295][La dificultad de entender el lenguaje que utilizan las Administraciones públicas]] #TextoClaro
+ [[https://minigpt-4.github.io/][MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models]] #VisualQuestionAnswering
+ [[https://resources.nvidia.com/en-us-omniverse-industrial-digital-twins/omniverse-enterprise-5-steps?lx=deNrXD][5 Steps to Get Started with Digital Twins]] #DigitalTwin #PRIMA
+ [[https://www.nvidia.com/en-us/on-demand/playlist/playList-7e07006c-7b01-4714-a0a5-c627b3707602/][Omniverse Digital Twin playlist]] #DigitalTwin #PRIMA
+ [[https://huggingface.co/blog/graphml-classification][Graph classification with Transformers]] #GraphNeuralNetworks
+ [[https://huggingface.co/blog/intro-graphml][Introduction to Graph Machine Learning]] #GraphNeuralNetworks
+ [[https://link.springer.com/book/10.1007/978-3-319-78503-5][Clinical Text Mining]] #HistoriaClinica #AnaRosaTerroba
+ [[https://www.youtube.com/playlist?list=PLqZXAkvF1bPNQER9mLmDbntNfSpzdDIU5][LangChain]] #PrevenIA
+ [[https://huyenchip.com/2023/04/11/llm-engineering.html][Building LLM applications for production]] #LanguageModels #PrevenIA
+ [[https://arxiv.org/pdf/2303.01469.pdf][Consistency Models]] #ImageGeneration
+ [[https://arxiv.org/abs/2210.03347][Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding]] #VisuallySituatedLanguage
+ [[https://mobile.twitter.com/NielsRogge/status/1644388959416352783][Extrayendo datos de gráficas]] #AngelLuis #Pix2Struct
+ [[https://blog.futuresmart.ai/semantic-search-using-llamaindex-and-langchain][Semantic Search using LlamaIndex and Langchain]] #SemanticSearch #PrevenIA
+ [[https://ai.googleblog.com/2023/04/developing-aging-clock-using-deep.html][Developing an aging clock using deep learning on retinal images]] #OPTRetina
+ [[https://arxiv.org/abs/2303.17580][HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in HuggingFace]] #NLP #ChatGPT
+ [[https://segment-anything.com/][Introducing Segment Anything: Working toward the first foundation model for image segmentation]] #Segmentation
+ [[https://www.sciencedirect.com/science/article/pii/S001048252300046X#b28][CARES: A Corpus for classification of Spanish Radiological reports]] #ClinicalText
+ [[https://enchanting-trader-463.notion.site/Best-ChatGPT-Resources-101-94a7c6dbabcc4febbfb498c555d6ef5f][Best ChatGPT Resources 101]] #ChatGPT
+ [[https://mobile.twitter.com/DotCSV/status/1611325175626072064][Midjourney prompts]] #ImageGeneration
+ [[https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/][Prompt Engineering]] #PromptEngineering
+ [[https://developer.nvidia.com/cuopt-logistics-optimization][NVIDIA cuOpt]] #OPTRetina #Planificacion
+ [[https://huggingface.co/spaces/merve/chatbot-blog][Ways to Improve Your Conversational Agents using Language Models]]
+ [[https://github.com/CarperAI/trlx][Transformer Reinforcement Learning X]] #RLHF #TextoClaro
+ [[https://huggingface.co/blog/rlhf][Illustrating Reinforcement Learning from Human Feedback (RLHF)]] #RLHF #TextoClaro
+ [[https://wandb.ai/ayush-thakur/RLHF/reports/Understanding-Reinforcement-Learning-from-Human-Feedback-RLHF-Part-1--VmlldzoyODk5MTIx][Understanding Reinforcement Learning from Human Feedback (RLHF): Part 1]] #RLHF
+ [[https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0282416][A deep learning-based framework for retinal fundus image enhancement]] #ImageEnhancement #OPTRetina

** Marzo 2023

+ [[https://www.sciencedirect.com/science/article/pii/S2589750023000225?via%3Dihub][A deep learning model for novel systemic biomarkers in photographs of the external eye: a retrospective study]] #OPTRetina
+ [[https://www.philschmid.de/fine-tune-flan-t5-peft][Efficient Large Language Model training with LoRA and Hugging Face]] #FineTuning #LLMs
+ [[https://t.co/OijUQQHr5g][Generative AI Models: History, Costs and Risks]] #Ethics #CIAIS
+ [[https://shikun.io/projects/prismer][Prismer: A Vision-Language Model with Multi-Modal Experts]] #MultiModalLearning #ImageCaptioning
+ [[https://huggingface.co/datasets/society-ethics/lila_camera_traps][Ethics & Society at Hugging Face]] #CIAIS

** Febrero 2023

+ [[https://txt.cohere.ai/what-is-semantic-search/][What is semantic search?]] #SemanticSearch #PrevenIA
+ [[https://huggingface.co/docs/transformers/main/en/tasks/image_captioning][Image captioning]] #ImageCaptioning
+ [[https://huggingface.co/blog/peft][PEFT: Parameter-Efficient Fine-Tuning of Billion-Scale Models on Low-Resource Hardware]] #Training #LanguageMondels
+ [[https://huggingface.co/spaces/whitead/paper-qa][Document Question and Answer]] #PrevenIA #HuggingFace
+ [[https://teachablemachine.withgoogle.com/][Teachable Machine]] #AutoML
+ [[https://github.com/m-bain/whisperX][WhisperX]] #SpeechRecognition #Diarization
+ [[https://twitter.com/LiJunnan0409/status/1620259379223343107][BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models]] #VisualQuestionAnswering
+ [[https://huggingface.co/blog/vision_language_pretraining][A Dive into Vision-Language Models]] #MultiModalLearning #ComputerVision #NLP
+ [[https://huggingface.co/spaces/kadirnar/BioGpt][M2M100 + BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining]] #HFSpace #BioQuestionAnswering
+ [[https://huggingface.co/spaces/vumichien/lip_movement_reading][Speech Recognition from Visual Lip Movement by Audio-Visual Hidden Unit BERT Model (AV-HuBERT)]] #LipMovementReading #HFSpace
+ [[https://huggingface.co/spaces/laion/CoCa][CoCa: Contrastive Captioners are Image-Text Foundation Models]] #CaptionGeneration #HFSpace
+ [[https://ljvmiranda921.github.io/notebook/2023/02/04/tagalog-pipeline/][Towards a Tagalog NLP pipeline]]

** Enero 2023

+ [[https://huggingface.co/blog/cv_state][The State of Computer Vision at Hugging Face 🤗]] #ComputerVision #HuggingFace
+ [[https://dmitry-kan.medium.com/neural-search-frameworks-a-head-to-head-comparison-976aa6662d20][Neural Search Frameworks: A Head-to-Head Comparison]] #SemanticSearch
+ [[https://cacm.acm.org/magazines/2018/3/225484-computational-social-science-computer-science-social-data/fulltext][Computational Social Science ≠ Computer Science + Social Data]] #CIAIS
+ [[https://huggingface.co/blog/mask2former][Universal Image Segmentation with Mask2Former and OneFormer]] #SemanticSegmentation #PanopticSegmentation
+ [[https://github.com/google-research/tuning_playbook][Deep Learning Tuning Playbook]] #HyperparameterTuning
+ [[https://txt.cohere.ai/sentence-word-embeddings/][What Are Word and Sentence Embeddings?]] #NLP
+ [[https://www.thelancet.com/journals/landig/article/PIIS2589-7500(22)00213-8/fulltext#%20][A non-invasive artificial intelligence approach for the prediction of human blastocyst ploidy: a retrospective model development and validation study]] #TesisMaria
+ [[https://blog.langchain.dev/langchain-chat/][LangChain Chat]] #PrevenIA #ChatBot
+ [[https://dsego.github.io/demystifying-fourier/][Demystifying Fourier analysis]] #Fourier
+ [[https://psynal.eu/mentescopia/][Educar en salud mental mejora la calidad de vida de las personas]] #PrevenIA
+ [[https://simonwillison.net/2023/Jan/13/semantic-search-answers/][How to implement Q&A against your documentation with GPT3, embeddings and Datasette]] #PrevenIA
+ [[https://research.latinxinai.org/papers/naacl/2022/pdf/paper_06.pdf][BioMedIA: A Complete Voice-to-Voice Generative Question Answering System for the Biomedical Domain in Spanish]] #QuestionAnswering
+ [[https://learnopencv.com/ultralytics-yolov8/][Ultralytics YOLOv8: State-of-the-Art YOLO Models]] #ObjectDetection
+ [[https://developer.nvidia.com/blog/reducing-development-time-for-intelligent-virtual-assistants-in-contact-centers/][Reducing Development Time for Intelligent Virtual Assistants in Contact Centers]] #PrevenIA
+ [[https://huggingface.co/docs/transformers/main/en/tasks/object_detection][Object detection]] #ObjectDetection #Transformers
+ [[https://arxiv.org/pdf/2212.13138.pdf][Large Language Models Encode Clinical Knowledge]] #MedicalQuestionAnswering #InstructionTuned
+ [[https://twitter.com/shl/status/1610359557905346560?s=20&t=ySW40mDN_YudGF1LbnfQkA][Chatbot]] #PrevenIA
+ [[https://weaviate.io/blog/2023/01/Hybrid-Search-Explained.html][Hybrid Search Explained]] #SemanticSearch
+ [[https://arxiv.org/abs/2301.00808][ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders]] #Classification #CNN
+ [[https://arxiv.org/abs/2212.12189][Stop using the elbow criterion for k-means and how to choose the number of clusters instead]] #Clustering #MachineLearning #IA
+ [[https://gist.github.com/yoavg/59d174608e92e845c8994ac2e234c8a9][Some remarks on Large Language Models]] #LanguageModels #ChatGPT
+ [[https://twitter.com/harishkgarg/status/1610202362358173696?s=20&t=E7WaIJPpYyiHoUIHU47jtg][Vector databases]] #SemanticSearch #PrevenIA
+ [[https://t.co/FSSpzATotz][Large Language Models Encode Clinical Knowledge]] #languagemodels #questionanswering #medicine
+ [[https://t.co/ASebqI7N4J][An overview of gradient descent optimization algorithms]] #machinelearning
+ [[https://t.co/M5M7E2MPiF][Bonjour. مرحبا. Guten tag. Hola. Cohere's Multilingual Text Understanding Model is Now Available]] #SemanticSearch #prevenia
+ [[https://arxiv.org/abs/2202.00911][Active Multi-Task Representation Learning]] #ActiveLearning #MultiTaskLearning
+ [[https://huggingface.co/tasks/conversational][Conversational]] #chatbots #prevenia
+ [[https://vkrakovna.wordpress.com/2022/06/02/paradigms-of-ai-alignment-components-and-enablers/][Paradigms of AI alignment]] #Alignment

* Lecturas del year 2022

** Diciembre 2022

+ [[https://e2eml.school/transformers.html][Transformers from Scratch]] #Transformers
+ [[https://www.deepset.ai/blog/what-is-text-vectorization-in-nlp][What Is Text Vectorization? Everything You Need to Know]] #PrevenIA 
+ [[https://twitter.com/lastpositivist/status/1607883482264666112][Ethics in AI Syllabus Liam Kofi Bright]] #Ethics
+ [[https://aws-fortuna.readthedocs.io/en/latest/][A Library for Uncertainty Quantification]] #Uncertainty
+ [[https://colab.research.google.com/drive/1bOIxb8cnpTrpMtTSBArY9FJlL59Ar4K_#scrollTo=tkFEP9jVS9Q4][Prompt node]] #Prompt #SemanticSearch
+ [[https://haystack.deepset.ai/tutorials/01_basic_qa_pipeline][Tutorial: Build Your First QA System]] #PrevenIA
+ [[https://ingenieriadesoftware.es/buscar-respuesta-documentos-qa-haystack/][COMO BUSCAR TU AGUJA EN UN PAJAR DE DATOS]] #PrevenIA
+ [[https://walkwithfastai.com/revisited/unknown.html][Recognizing Unknown Images, or the Unknown Label Problem]] #FastAI #OutOfDomain
+ [[https://speechbrain.github.io/index.html][SpeechBrain]] #Mirari
+ [[https://www.santiagomartin.dev/blog/resumico-el-bot-que-resume-audios-de-whatsapp-parte-uno][resumico, el bot que resume audios de WhatsApp]] #PrevenIA #Whatsapp
+ [[https://arxiv.org/pdf/1704.00051.pdf][Reading Wikipedia to Answer Open-Domain Questions]] #PrevenIA #QuestionAnswering
+ [[https://colab.research.google.com/drive/1mnArj9S7cij3Ua-dHXoasKWqyNA-GCrT?usp=sharing][Audio classification with Vision Transformers]] #AudioClassification
+ [[https://arxiv.org/abs/2212.09748][Scalable Diffusion Models with Transformers]] #Transformers #Diffusion
+ [[https://aclanthology.org/2022.acl-long.458/][The AI Doctor Is In: A Survey of Task-Oriented Dialogue Systems for Healthcare Applications]] #ChatBot #PrevenIA
+ [[https://huggingface.co/blog/clipseg-zero-shot][Zero-shot image segmentation with CLIPSeg]] #ZeroShotLearning #SemanticSegmentation
+ [[https://huggingface.co/blog/time-series-transformers][Probabilistic Time Series Forecasting with 🤗 Transformers]] #TimeSeries
+ [[https://arxiv.org/abs/2209.00626][The alignment problem from a deep learning perspective]] #Alignment #DeepLearning
+ [[https://arxiv.org/abs/2212.06727][What do Vision Transformers Learn? A Visual Exploration]] #VisionTransformers #Interpretation
+ [[https://github.com/besacier/ASR2022][Automatic Speech Recognition: Introduction, Current Trends and Open Problems]] #ASR #Mirari
+ [[https://huggingface.co/spaces/society-ethics/disaggregators][Exploring Disaggregated Data with 🤗 Disaggregators]] #Ethics
+ [[https://docs.google.com/presentation/d/1LVnwWShIVNVBxA8eG017zsDioP7BnT7DHc8eU0NGC3E/edit#slide=id.g14ba08db4d3_0_164][Few-Shot Learning In Production]] #SetFit #FewShotLearning #Transformers
+ [[https://crfm.stanford.edu/2022/12/15/pubmedgpt.html][PubMedGPT 2.7B]] #TextoClaro #BiomedicalTexts 
+ [[https://www.mosaicml.com/blog/introducing-pubmed-gpt][PubMed GPT: a Domain-Specific Large Language Model for Biomedical Text]] #TextoClaro #BiomedicalTexts 
+ [[https://github.com/huggingface/notebooks/blob/main/examples/semantic_segmentation.ipynb][Fine-tuning for Semantic Segmentation with 🤗 Transformers]] #SemanticSegmentation
+ [[https://aclanthology.org/2022.slpat-1.7/][On the Ethical Considerations of Text Simplification]] #TextSimplification #TextoClaro #ClaraMed
+ [[https://github.com/UKPLab/EasyNMT][EasyNMT - Easy to use, state-of-the-art Neural Machine Translation]] #MachineTranslation #MasterArista
+ [[https://www.nature.com/articles/s41598-021-89743-x][Predicting sex from retinal fundus photographs using automated deep learning]] #UPRetina
+ [[https://simplemlforsheets.com/tutorial.html][Simple ML for Sheets]] #Drive #MachineLearning
+ [[https://colab.research.google.com/drive/17Hu1pxqhfMisjkSgmM2CnZxfqDyn2hSY?usp=sharing][Fine-tuning or using Whisper, wav2vec2, HuBERT and others with SpeechBrain and HuggingFace]] #Whisper #FineTuning
+ [[https://huggingface.co/blog/deep-learning-with-proteins][Deep Learning With Proteins]] #Chemistry
+ [[https://repositorio.uam.es/handle/10486/692479][Cómo construir un psicólogo-chatbot]] #PrevenIA
+ [[https://www.youtube.com/attribution_link?a=zuVCqqpo5nImhbLd&u=/watch%3Fv%3DfZMiD8sDzzg%26feature%3Dem-lbrm][Whisper Fine Tuning Event]] #ASR

** Noviembre 2022

+ [[https://arxiv.org/pdf/2211.16158.pdf][Out-Of-Distribution Detection Is Not All You Need]] #OutOfDistribution
+ [[https://arxiv.org/pdf/2202.11748.pdf][The Need for Interpretable Features: Motivation and Taxonomy]] #Interpretability
+ [[https://neurips.ml.gatech.edu/artificial-agents-use-reinforcement-learning-to-explain-actions-a-necessary-step-as-they-get-smarter-at-accomplishing-tasks/][Artificial Agents Use Reinforcement Learning to Explain Actions, a Necessary Step as They Get Smarter]] #ReinforcementLearning #Interpretability
+ [[https://img.ly/blog/ultimate-guide-to-ffmpeg/][FFmpeg - The Ultimate Guide]] #Video
+ [[https://stability.ai/blog/stable-diffusion-v2-release][Stable Diffusion 2.0 Release]] #Diffusion
+ [[https://e-space.mmu.ac.uk/623484/1/clinicalNTS.pdf][Neural Text Simplification of Clinical Letters with a Domain Specific Phrase Table]] #TextSimplification #ClaraMED
+ [[https://developers.google.com/search/docs/appearance/ranking-systems-guide][A guide to Google Search ranking systems]] #SearchSystems
+ [[https://arxiv.org/abs/2211.00611][MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Model]] #DiffusionModels #SemanticSegmentation
+ [[https://vincentlepetit.github.io/files/paper_writing.pdf][Writing a Good Research Paper]] #PhD
+ [[https://twitter.com/RisingSayak/status/1592389454026506240?s=20&t=PHSfKY-7qxQe2am2ez9Abw][Video Classification]] #VideoClassification
+ [[https://philippschmitt.com/blueprints-for-intelligence/][Blueprints for intelligence]] #History #Diagrams
+ [[https://dl.acm.org/doi/pdf/10.1145/3374217][Adversarial Attacks on Deep-learning Models in Natural Language Processing: A Survey]]
+ [[https://arxiv.org/abs/2005.05909][TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP]] #NLP #AdversarialAttacks #Mapi [[https://github.com/QData/TextAttack][libraryhttps://github.com/QData/TextAttack]]
+ [[https://www.youtube.com/watch?v=Sv7rI-iFvXI][Accelerating ML Inference at Scale with ONNX, Triton and Seldon | PyData Global 2021]] #ONNX #Production #OPTRetina
+ [[https://community.wandb.ai/t/taking-fastai-to-production/1705][Taking FastAI to Production]] #FastAI #Production #OPTRetina
+ [[https://www.vice.com/en/article/y3pezm/scientists-increasingly-cant-explain-how-ai-works][Scientists Increasingly Can’t Explain How AI Works]] #Explainability #Mapi
+ [[https://docs.fast.ai/tutorial.image_sequence.html][Image sequences]] #FastAI #Video
+ [[https://github.com/NVIDIA/NeMo][NVIDIA NeMo]] #SpeechRecognition #Mirari [[https://colab.research.google.com/gist/titu1994/080c5387c4c02b41ce79dd4405d87104#scrollTo=L4y7itGOancP][Transfer learning]] [[https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/stable/starthere/tutorials.html][Tutorials]]
+ [[https://huggingface.co/blog/fine-tune-whisper][Fine-Tune Whisper For Multilingual ASR with 🤗 Transformers]] #SpeechRecognition #Mirari
+ [[https://txt.cohere.ai/introducing-sandbox-coheres-experimental-open-source-initiative/][Introducing Cohere Sandbox: Open-Source Libraries to Help Developers Experiment with Language AI]] #Psicologos #Chatbot [[https://github.com/cohere-ai/sandbox-accelerating-chatbot-training][repositorio1]] [[https://github.com/cohere-ai/sandbox-toy-semantic-search][repositorio2]]
+ [[http://konect.cc/networks/eat/][Edinburgh Associative Thesaurus]]
+ [[https://ai.googleblog.com/2022/03/detecting-signs-of-disease-from.html][Detecting Signs of Disease from External Images of the Eye]] #UPRetina
+ [[https://ibm.github.io/model-recycling/][model-recycling page]] #NLP #TransferLearning

** Octubre 2022

+ [[https://www.sciencedirect.com/science/article/pii/S0002939420303846#appsec1][Retinal Vasculometry Associations With Glaucoma: Findings From the European Prospective Investigation of Cancer–Norfolk Eye Study]] #OPTRetina
+ [[https://arxiv.org/pdf/2210.11416.pdf][Scaling Instruction-Finetuned Language Models]] #ZeroShotLearning
+ [[https://twitter.com/ai__pub/status/1584152707622846466?s=20&t=oA2kHVNl5dYpr-iyeircOw][Neural Radiance Fields (NeRFs), Explained]] #NERFS #Roberto
+ [[https://github.com/HenriquesLab/ZeroCostDL4Mic][ZeroCostDL4Mic: exploiting Google Colab to develop a free and open-source toolbox for Deep-Learning in microscopy]] #Democratization #DeepLearning
+ [[https://arxiv.org/abs/2202.08341][Anomalib: A Deep Learning Library for Anomaly Detection]] #AnomalyDetection #PabloAscorbe [[https://github.com/openvinotoolkit/anomalib][library]]
+ [[https://www.cognitivefactory.fr/fastaidocs/][FastAI Concepts]] #FastAI
+ [[https://arxiv.org/pdf/2103.10158.pdf][TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation]] #DataAugmentation
+ [[https://link.springer.com/chapter/10.1007/978-3-319-54181-5_14][FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-Based CNN Architecture]] #Depth #Segmentation #Roberto
+ [[https://huggingface.co/blog/introducing-doi][Introducing DOI: the Digital Object Identifier to Datasets and Models]] #DOIs
+ [[https://pyimagesearch.com/2022/10/17/thermal-vision-measuring-your-first-temperature-from-an-image-with-python-and-opencv/?utm_Source=Drip&utm_Medium=Email&utm_Campaign=WeeklyUpdate&utm_Content=17Oct2022NonUniv1][Thermal Vision: Measuring Your First Temperature from an Image with Python and OpenCV]] #ImagenesTermicas #Zataca
+ [[https://pyimagesearch.com/2022/10/10/introduction-to-infrared-vision-near-vs-mid-far-infrared-images/][Introduction to Infrared Vision: Near vs. Mid-Far Infrared Images]]  #ImagenesTermicas #Zataca
+ [[https://www.cs197.seas.harvard.edu/][AI Research Experiences Harvard CS197]] #Phd
+ [[https://docs.google.com/document/u/0/d/15pnUpD47S6mAM-g4fwQvc2klYIb-GKgWex1oOlmNjvg/mobilebasic?urp=gmail_link][CS197 Harvard: AI Research Experiences]] #PhD
+ [[https://users.soe.ucsc.edu/~milanfar/publications/journal/ModernTour.pdf][A tour of Modern Image Filtering]] #Filters #Denoising
+ [[https://www.deepmind.com/blog/discovering-novel-algorithms-with-alphatensor?utm_campaign=AlphaTensor][Discovering novel algorithms with AlphaTensor]] #MatrixMultiplication #ReinforcementLearning
+ [[https://towardsdatascience.com/quantum-deep-learning-a-quick-guide-to-quantum-convolutional-neural-networks-d65284e21fc4][Quantum Deep Learning: A Quick Guide to Quantum Convolutional Neural Networks]] #QuantumComputing #DeepLearning
+ [[https://erictopol.substack.com/p/the-amazing-power-of-machine-eyes][The amazing power of "machine eyes"]] #Retina #OPTRetina
+ [[https://www.youtube.com/watch?v=NcqfHa0_YmU][Stanford CS224N NLP with Deep Learning | Winter 2021 | Lecture 11 - Question Answering]] #QuestionAnswering #Psicologos
+ [[https://jalammar.github.io/illustrated-stable-diffusion/][The Illustrated Stable Diffusion]] #Diffusion
+ [[https://dl.acm.org/doi/abs/10.1145/3546036][Interpretable machine learning: moving from mythos to diagnostics]] #Interpretability
+ [[https://arxiv.org/abs/2209.14974][Greybox XAI: a Neural-Symbolic learning framework to produce interpretable predictions for image classification]] #Interpretability
+ [[https://www.wired.co.uk/article/mental-health-chatbots][The Problem With Mental Health Bots]] #Chatbots
+ [[https://cameronrwolfe.substack.com/p/vision-transformers][Vision Transformers ... is using them actually worth it?]] #Transformers

** Septiembre 2022

+ [[https://github.com/NielsRogge/Transformers-Tutorials][Transformers Tutorials]] #Transformers #Tutorials
+ [[https://arxiv.org/pdf/1705.07750.pdf][Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset]] #ActionRecognition
+ [[https://huggingface.co/inference-endpoints][Transformers in production: solved]] #Inference
+ [[https://huggingface.co/sentence-transformers][Sentence Transformers]] #SemanticSearch #Embeddings 
+ [[https://www.youtube.com/watch?v=AwJf8aQfChE][OpenAI Whisper: Robust Speech Recognition via Large-Scale Weak Supervision | Paper and Code]] #SpeechRecognition
+ [[https://arxiv.org/pdf/2209.12356.pdf][News Summarization and Evaluation in the Era of GPT-3]] #Summarization #TextoClaro
+ [[https://huggingface.co/blog/accelerate-large-models][How 🤗 Accelerate runs very large models thanks to PyTorch]] #HuggingFace #Inference
+ [[https://huggingface.co/blog/setfit][SetFit: Efficient Few-Shot Learning Without Prompts]] #FewShotLearning #TextoClaro
+ [[https://cdn.openai.com/papers/whisper.pdf][Robust Speech Recognition via Large-Scale Weak Supervision]] #SpeechRecognition #Gobierno
+ [[https://www.trustworthyml.org/resources][Trustworthy ML]] #Resources #Fairness #Interpretability
+ [[https://cloud.google.com/blog/topics/developers-practitioners/find-anything-blazingly-fast-googles-vector-search-technology][Find anything blazingly fast with Google's vector search technology]] #SemanticSearch
+ [[https://github.com/deepset-ai/haystack][HayStack]] #SemanticSearch #Library
+ [[https://transformer-circuits.pub/2022/toy_model/index.html][Toy Models of Superposition]] #Interpretability
+ [[https://docs.google.com/presentation/d/1ZXFIhYczos679r70Yu8vV9uO6B1J0ztzeDxbnBxD1S0/edit#slide=id.g31364026ad_3_2][Transformers]] #Transformers #Slides
+ [[https://arxiv.org/abs/2209.04836][Git Re-Basin: Merging Models modulo Permutation Symmetries]] #ModelCombination
+ [[https://huggingface.co/blog/diffusers-2nd-month][What's new in Diffusers? 🎨]] #DiffusionModels #HuggingFace
+ [[https://github.com/sharonzhou/long_stable_diffusion][Long Stable Diffusion: Long-form text to images]] #Diffusion #ImageGeneration
+ [[https://www.philschmid.de/fine-tuning-donut][Document AI: Fine-tuning Donut for document-parsing using Hugging Face Transformers]] #HuggingFace #NLP #Recibos #Invoices
+ [[https://huggingface.co/blog/train-decision-transformers][Train your first Decision Transformer]] #Transformers #HuggingFace #ReinforcementLearning
+ [[https://dienhoa.github.io/dhblog/SSD_base.html][Object Detection - Single Shot Detector for fastai V2]] #ObjectDetection #FastAI
+ [[https://e2eml.school/transformers.html][Transformers from Scratch]] #Transformers #NLP
+ [[https://colab.research.google.com/drive/1dlgggNa5Mz8sEAGU0wFCHhGLFooW_pf1?usp=sharing#scrollTo=yMRl4sMSK0rh][Grokking Stable Diffusion]] #StableDifussion
+ [[https://github.blog/2020-12-18-learn-about-ghapi-a-new-third-party-python-client-for-the-github-api/][Learn about ghapi, a new third-party Python client for the GitHub API]] #GitHub #Python
+ [[https://hal.archives-ouvertes.fr/hal-03723551][Why do tree-based models still outperform deep learning on tabular data?]] #TabularData #Trees #NNs
+ [[https://bastian.rieck.me/blog/posts/2022/open_source/][Open Source and Academia]] #OpenSource
+ [[https://muellerzr.github.io/fastblog/2021/02/14/Pytorchtofastai.html][Pytorch to fastai, Bridging the Gap]] #Pytorch #FastAI
+ [[https://docs.fast.ai/examples/migrating_pytorch_verbose.html][Pytorch to fastai details]] #Pytorch #FastAI
+ [[https://github.com/RasaHQ/rasa][Rasa Open Source]] #Chatbots

** Agosto 2022

+ [[https://youtu.be/xSGX8gBQDO8][large language models for real world applications]] #nlp #LanguageModels 
+ [[https://youtu.be/J87hffSMB60][How does Stable Diffusion work? – Latent Diffusion Models EXPLAINED]] #StableDifussion
+ [[https://cse.msu.edu/~mayao4/dlg_book/][Deep Learning on Graphs]] #GraphNeuralNetworks #Book
+ [[https://www.youtube.com/playlist?list=PLfYUBJiXbdtSLBPJ1GMx-sQWf6iNhb8mM][FastAI live coding]] #tips #tricks #basics
+ [[https://arxiv.org/abs/1409.0473][Neural Machine Translation by Jointly Learning to Align and Translate]] #NLP #Translation
+ [[https://www.inference.vc/the-east-european-guide-to-writing-reference-letters/][Eastern European Guide to Writing Reference Letters]]
+ [[https://mobile.twitter.com/MushtaqBilalPhD/status/1562709453996060673][Zotero]] #phd
+ [[https://thesequence.substack.com/p/-natural-language-understanding-recap][Natural Language Understanding Recap]] #NLP
+ [[https://ai.facebook.com/blog/blenderbot-3-a-175b-parameter-publicly-available-chatbot-that-improves-its-skills-and-safety-over-time/][BlenderBot 3: A 175B parameter, publicly available chatbot that improves its skills and safety over time]] #ChatBot #NLP
+ [[https://thegradientpub.substack.com/p/the-future-of-speech-recognition?utm_source=substack&utm_medium=email][The Future of Speech Recognition: Where Will We Be in 2030?]] #SpeechRecognition #Comunidad
+ [[https://danielvanstrien.xyz/huggingface/huggingface-datasets/transformers/2022/08/16/detr-object-detection.html][Training an object detection model using Hugging Face]] #ObjectDetection #Transformers #HuggingFace
+ [[https://twitter.com/fede_gr/status/1559943993726832645?s=20&t=86pVLAoIIeyXfekf755aJA][StatsForecast Exponential Smoothing (ETS)]] #Forecasting #Zataca
+ [[https://fleuret.org/dlc/][DEEP LEARNING COURSE]] #DeepLearning #Course
+ [[https://sites.temple.edu/borguet/files/2020/09/1-s2.0-S0009912019312019-main.pdf][How to write (and how not to write) a scientific review article]] #Phd
+ [[https://programminghistorian.org/en/lessons/computer-vision-deep-learning-pt1][Computer Vision for the Humanities: An Introduction to Deep Learning for Image Classification]] #MasterArista #ComputerVision
+ [[https://web.stat.tamu.edu/~suhasini/teaching673/time_series.pdf][A course in Time Series Analysis]] #TimeSeries #Zataca
+ [[https://huggingface.co/blog/stable_diffusion][Stable Diffusion with 🧨 Diffusers]] #Diffusion #HuggingFace
+ [[https://mobile.twitter.com/VisionBernie/status/1562385340819820544][How to do research]] #phd
+ [[https://pyimagesearch.com/2022/08/10/computer-vision-and-deep-learning-for-agriculture/][Computer Vision and Deep Learning for Agriculture]] #agriculture #computervision #applications
+ [[https://arxiv.org/abs/2203.05482][Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time]] #Ensemble
+ [[https://t.co/SGKpqXAufF][using deep learning when class labels have an order]] #order
+ [[https://joinup.ec.europa.eu/collection/catalogue-services/document/study-natural-language-processing-public-services
][Study: Natural Language Processing for Public Services]] #NLP #Comunidad

** Julio 2022

+ [[https://www.philschmid.de/optimize-sentence-transformers][sentence transformers]] #semanticsearch
+ [[https://www.natalieparde.com/files/NLG4Health%20%40%20INLG%202022.pdf][ The AI Doctor is in]] #chatbot #healthcare 
+ [[https://arxiv.org/abs/2207.07048][Leakage and the Reproducibility Crisis in ML-based Science]] #Reproducibility #DataLeakage
+ [[https://arxiv.org/pdf/2207.09238.pdf][Formal Algorithms for Transformers]] #Transformers #Algorithms
+ [[https://www.nature.com/articles/s41746-022-00613-w][Prostate cancer therapy personalization via multi-modal deep learning on randomized phase III clinical trials]] #MultiModalLearning
+ [[https://arxiv.org/abs/2203.03605][DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection]] #ObjectDetection #Transformers
+ [[https://reproducible.cs.princeton.edu/][Leakage and the Reproducibility Crisis in ML-based Science]] #DataLeakage #Reproducibility
+ [[https://knowingmachines.org/reading-list][Critical Dataset Studies Reading List]] #Datasets
+ [[https://huggingface.co/blog/bloom-megatron-deepspeed][The Technology Behind BLOOM Training]] #HuggingFace #LanguageModels #Parallelism
+ [[https://www.sciencedirect.com/science/article/pii/S1568494621011303][End-to-end multi-task learning for simultaneous optic disc and cup segmentation and glaucoma classification in eye fundus images]] #MultiTaskLearning #Glaucoma
+ [[https://hal.archives-ouvertes.fr/hal-03590892/document][Multi-task deep learning for glaucoma detection from color fundus images]] #MultiTaskLearning #Glaucoma
+ [[https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8001225/][Explainable Machine Learning Model for Glaucoma Diagnosis and Its Interpretation]] #OPTRetina #Glaucoma
+ [[https://arxiv.org/abs/2207.03620][More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity]] #Vision #CNNs
+ [[https://arxiv.org/abs/2207.02696][YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors]] #ObjectDetection
+ [[https://github.com/cmhungsteve/Awesome-Transformer-Attention][Ultimate-Awesome-Transformer-Attention]] #Attention #Vision
+ [[https://laurenoakdenrayner.com/2022/07/04/no-doctor-required-autonomy-anomalies-and-magic-puddings/][No Doctor Required: Autonomy, Anomalies, and Magic Puddings]] #Ethics #AnomalyDetection
+ [[https://twitter.com/espejelomar/status/1544367888357658625?s=20&t=0FWH6Dh9HvHRd40fNNYejQ][Sentence transformers]] #SentenceEmbeddings #SemanticSearch #HuggingFace
+ [[https://www.nature.com/articles/s41598-020-80839-4][Predicting intraocular pressure using systemic variables or fundus photography with deep learning in a health examination cohort]] #IOP #OPTRetina

** Junio 2022

+ [[https://twitter.com/CamachoCollados/status/1542344272762003456][tweetnlp]] #NLP 
+ [[https://github.com/cbail/comp_soc_grad][computational social science course]] #MasterArista
+ [[https://huggingface.co/blog/annotated-diffusion][The Annotated Diffusion Model]] #Diffusion
+ [[https://huggingface.co/blog/eval-on-the-hub][Announcing Evaluation on the Hub]] #HuggingFace #Evaluation
+ [[https://www.youtube.com/playlist?list=PLo2EIpI_JMQtyEr-sLJSy5_SnLCb4vtQf][Hugging Face Tasks]] #HuggingFace #MasterArista
+ [[https://keras.io/examples/nlp/active_learning_review_classification/][Review Classification using Active Learning]] #ActiveLearning
+ [[https://arxiv.org/pdf/2110.00023.pdf][Mining for strong gravitational lenses with self-supervised learning]] #SelfSupervisedLearning
+ [[https://arxiv.org/pdf/2205.11423.pdf][Decoder Denoising Pretraining for Semantic Segmentation]] #SemanticSegmentation #DifussionModels #Pretraining
+ [[https://cvpr2022-tutorial-diffusion-models.github.io/][Denoising Diffusion-based Generative Modeling: Foundations and Applications]] #Denoising
+ [[https://www.kaggle.com/code/jhoward/the-best-vision-models-for-fine-tuning][The best vision models for fine-tuning]] #FastAI #Timm
+ [[https://www.nature.com/articles/s41598-017-17876-z][Leveraging uncertainty information from deep neural networks for disease detection]] #OPTRetina #OutOfDistribution
+ [[https://github.com/huggingface/diffusers][Diffusers]] #Diffusion #Huggingface
+ [[https://www.analyticsinsight.net/top-10-python-libraries-for-time-series-analysis-in-2022/][TOP 10 PYTHON LIBRARIES FOR TIME SERIES ANALYSIS IN 2022]] #Zataca #Forecasting 
+ [[https://www.kaggle.com/code/anmolgupta11090/jpx-tokyo-stock-prediction-with-nvidia-tspp][JPX Tokyo Stock Prediction with NVIDIA-TSPP]] #Zataca #Forecasting 
+ [[https://hal.archives-ouvertes.fr/hal-03682454v3/document][Evaluating machine learning models and their diagnostic value]] #Evaluation
+ [[https://sebastianraschka.com/blog/2022/confidence-intervals-for-ml.html][Creating Confidence Intervals for Machine Learning Classifiers]] #ConfidenceIntervals #Statistics
+ [[https://sebastianraschka.com/blog/2021/dl-course.html#l19-self-attention-and-transformer-networks][Introduction to Deep Learning]] #DeepLearning #Course
+ [[https://arxiv.org/abs/2105.05837][When Does Contrastive Visual Representation Learning Work?]] #SelfSupervisedLearning
+ [[https://machinelearningmastery.com/how-to-develop-lstm-models-for-multi-step-time-series-forecasting-of-household-power-consumption/][Multi-Step LSTM Time Series Forecasting Models for Power Usage]] #Zataca #Forecasting 
+ [[http://www.phontron.com/class/multiling2022/schedule.html][CMU Multilingual NLP 2022]] #MasterArista [[https://www.youtube.com/playlist?list=PL8PYTP1V4I8BhCpzfdKKdd1OnTfLcyZr7][Videos]]
+ [[https://github.com/Nixtla/neuralforecast][Deep Learning for time series]] #Zataca #Forecasting [[https://github.com/Nixtla/neuralforecast/blob/main/examples/mqnhits.ipynb][Repository]] [[https://github.com/Nixtla/neuralforecast][Example]]
+ [[https://dl.acm.org/doi/full/10.1145/3485128][Tackling Climate Change with Machine Learning]]
+ [[https://arxiv.org/pdf/2202.08978.pdf][Cyclical Focal Loss]] #ImbalancedData
+ [[https://arxiv.org/abs/2205.10337][UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes]] #ComputerVision
+ [[https://colab.research.google.com/github/gdsbook/book/blob/master/notebooks/08_point_pattern_analysis.ipynb#scrollTo=coated-terry][Point Pattern Analysis]] #Innozone
+ [[https://github.com/allenai/acl2022-zerofewshot-tutorial][ACL 2022 Tutorial: Zero- and Few-Shot NLP with Pretrained Language Models]] #NLP

** Mayo 2022

+ [[https://arxiv.org/abs/2112.13492][Vision Transformer for Small-Size Datasets]] #Transformers #ComputerVision
+ [[https://jarvislabs.ai/blogs/hf-getting-started/][Huggingface 🤗 is all you need for NLP and beyond]] #NLP #MasterArista
+ [[http://web.stanford.edu/class/cs224n/][CS224n: Natural Language Processing with Deep Learning]] #NLP
+ [[https://nlp-css-201-tutorials.github.io/nlp-css-201-tutorials/][NLP+CSS 201 Tutorials]] #MasterArista
+ [[https://sicss.io/curriculum][Open source teaching and learning resources for computational social science]] #MasterArista
+ [[https://sites.google.com/view/esslli2019-nlp/w1?authuser=0][Introduction to NLP with Python]] #NLP #MasterArista
+ [[https://hackingsemantics.xyz/2019/nlp4linguists/][How to teach NLP to non-CS-majors in 2 weeks?]] #NLP #MasterArista
+ [[https://www.fast.ai/2022/05/17/societal-harms/][AI Harms are Societal, Not Just Individual]] #Ethics
+ [[https://github.com/jdb78/pytorch-forecasting][PyTorch Forecasting]] #Zataca #Forecasting 
+ [[https://nlp-css-201-tutorials.github.io/nlp-css-201-tutorials/][Tutorials for advanced natural language processing methods designed for computational social science research.]] #NLP #MasterArista
+ [[https://arxiv.org/abs/2205.06743][A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities]] #FewShotLearning #Survey
+ [[https://developers.google.com/machine-learning/guides/text-classification/step-2-5][Text classification]] #NLP #MasterArista
+ [[https://towardsdatascience.com/neural-sheaf-diffusion-for-deep-learning-on-graphs-bfa200e6afa6][Neural Sheaf Diffusion for deep learning on graphs]] #GNNs #Topology
+ [[https://storage.googleapis.com/deepmind-media/A%20Generalist%20Agent/Generalist%20Agent.pdf][A Generalist Agent]] #MultiModal
+ [[https://arxiv.org/pdf/2006.06676.pdf][Training Generative Adversarial Networks with Limited Data]] #GANs #Retina [[https://github.com/NVlabs/stylegan2-ada-pytorch][Code]]
+ [[https://twitter.com/SomosNLP_/status/1525165918594158595][Hackaton NLP]] #NLP #Espyearl #MasterArista

** Abril 2022

+ [[https://thegradient.pub/the-role-of-deep-learning-in-understanding-neuroimaging-data/][Deep Learning in Neuroimaging]] #NeuroImaging
+ [[https://github.com/huggingface/deep-rl-class][Reinforcement Learning course]] #ReinforcementLearning HuggingFace
+ [[https://huggingface.co/blog/fastai][Welcome fastai to the Hugging Face Hub]] #FastAI #HuggingFace
+ [[https://www.technologyreview.com/2022/04/20/1050392/ai-industry-appen-scale-data-labels/][How the AI industry profits from catastrophe]] #Ethics
+ [[https://dicksonneoh.com/portfolio/how_to_deploy_od_models_on_android_with_flutter/][How to Deploy Object Detection Models on Android with Flutter]] #Deployment #HuggingFace #Mobile #Gradio
+ [[https://www.deepmind.com/blog/tackling-multiple-tasks-with-a-single-visual-language-model][Tackling multiple tasks with a single visual language model]] #ComputerVision #NLP
+ [[https://medium.com/@beenkim/beyond-interpretability-4bf03bbd9394][ Beyond interpretability: developing a language to shape our relationships with AI]] #interpretability 
+ [[https://ai.googleblog.com/2022/04/pix2seq-new-language-interface-for.html][Pix2Seq: A New Language Interface for Object Detection]] #objectdetection  #nlp
+ [[https://www.technologyreview.com/2022/04/19/1049592/artificial-intelligence-colonialism/][Artificial intelligence is creating a new colonial world order]] #Ethics
+ [[https://www.kaggle.com/code/jhoward/getting-started-with-nlp-for-absolute-beginners/notebook][Getting started with Kaggle, NLP and HuggingFace for absolute beginners]] #Kaggle #NLP
+ [[https://www.kaggle.com/code/jhoward/iterate-like-a-grandmaster/notebook][Iterate like a grandmaster]] #Kaggle #NLP
+ [[https://arxiv.org/abs/2004.12150][A Survey on Incorporating Domain Knowledge into Deep Learning for Medical Image Analysis]] #MedicalAI
+ [[https://ieeexplore.ieee.org/document/7966398][Monthly energy consumption forecast: A deep learning approach]] #Zataca 
+ [[https://innovations.bmj.com/content/bmjinnov/6/2/45.full.pdf][Bridging the implementation gap of machine learning in healthcare]] #MedicalAI 
+ [[https://amitness.com/2020/05/data-augmentation-for-nlp/][A Visual Survey of Data Augmentation in NLP]] #NLP #DataAugmentation
+ [[https://arxiv.org/abs/1912.09363][Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting]] #TimeSeriesForecasting #Zataca
+ [[https://arxiv.org/abs/1703.07015][Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks]] #TimeSeriesForecasting #Zataca
+ [[https://arxiv.org/abs/1905.03806][Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting]] #TimeSeriesForecasting #Zataca
+ [[https://www.sciencedirect.com/science/article/pii/S2589750022000048][Validation and algorithmic audit of a deep learning system for the detection of proximal femoral fractures in patients in the emergency department: a diagnostic accuracy study]] #Audit #ArtificialIntelligence #Medicine
+ [[https://www.sciencedirect.com/science/article/pii/S2589750022000036][The medical algorithmic audit]] #Audit #ArtificialIntelligence #Medicine
+ [[https://arxiv.org/abs/2203.02486][The Familiarity Hypothesis: Explaining the Behavior of Deep Open Set Methods]] #AnomalyDetection #OpenSet


** Marzo 2022

+ [[https://rish-16.github.io/posts/gnn-math/][Math Behind Graph Neural Networks]] #GraphNeuralNetworks #TFGRaquel
+ [[https://t.co/NGj1UmGFH1][Stanford Graph Learning Workshop]] #GraphNeuralNetworks
+ [[https://karpathy.github.io/2022/03/14/lecun1989/][Deep Neural Nets: 33 years ago and 33 years from now]] #DeepLearning
+ [[https://github.com/nathanhubens/fasterai][Fasterai: A library to make smaller and faster neural networks]] #Pruning #FastAI
+ [[https://horace.io/brrr_intro.html][Making Deep Learning Go Brrrr From First Principles]] #GPUs
+ [[https://huggingface.co/blog/decision-transformers][Introducing Decision Transformers on Hugging Face 🤗]] #ReinforcementLearning #HuggingFace
+ [[https://twitter.com/duygu_islakoglu/status/1505588164458692619?s=20&t=KchyJM1nAMvs-NpSXwHFbg][AI ethics collection]] #Ethics
+ [[https://youtu.be/GX4l3WhOy4o][IA y PLN, una apasionante encrucijada]] #NLP #MasterArista
+ [[https://www.nih.gov/news-events/news-releases/attention-objects-peripheral-vision-not-driven-tiny-eye-movements][Attention to objects in peripheral vision is not driven by tiny eye movements]] #Vision
+ [[https://youtu.be/344w5h24-h8][Diffusion models explained. How does OpenAI's GLIDE work?]] #DifussionModels
+ [[https://www.youtube.com/watch?v=UQwWTykNFW0][MUESTREO DE DATOS: MUESTREO BASADO EN PERPLEJIDAD]] #NLP
+ [[https://www.youtube.com/watch?v=U8fig2fqrl8][Traducción Automática con Eva Martínez Garcia - Hackathon de NLP en Espyearl]] #TraduccionAutomatica #MasterArista #NLP
+ [[https://www.marekrei.com/blog/mphil-project-advice/][Advice for students doing research projects in ML/NLP]] #MLProjects
+ [[https://nlp-ensae.github.io/][NLP Course]] #NLP #MasterArista
+ [[https://snap.stanford.edu/graphlearning-workshop/][Stanford Graph Learning Workshop]] #GraphNeuralNetworks
+ [[https://huggingface.co/blog/bert-101][BERT 101 🤗 State Of The Art NLP Model Explained]] #NLP #MasterArista
+ [[https://www.youtube.com/watch?v=3WXhnQr4ADQ][Introduction to Graph Neural Network]] #GraphNeuralNetworks
+ [[https://arxiv.org/pdf/2101.02118.pdf][Do We Really Need Deep Learning Models for Time Series Forecasting?]] #TimeSeries #Zataca
+ [[https://www.sciencedirect.com/science/article/pii/S1361841519301100][REFUGE Challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs]] #OPTRetina #Glaucoma
+ [[https://arxiv.org/abs/2202.06709v1][How Do Vision Transformers Work?]] #Transformers #Vision
+ [[http://web.stanford.edu/class/cs224n/][CS224n: Natural Language Processing with Deep Learning]] #NLP #Course

** Febrero 2022

+ [[https://huggingface2.notion.site/Education-Toolkit-7b4a9a9d65ee4a6eb16178ec2a4f3599][🤗 Education Toolkit]] #HuggingFace #Course
+ [[https://colab.research.google.com/drive/1K5tP5NBWwtezBg3Kp4wpD5KI6JZ6oCg9][Building and Hosting Machine Learning Demos with Gradio & Hugging Face]] #Gracdio #HuggingFace
+ [[http://www.bertforhumanists.org/tutorials/][BERT for Humanists]] #NLP #MasterArista
+ [[https://towardsdatascience.com/getting-started-with-pytorch-image-models-timm-a-practitioners-guide-4e77b4bf9055][Getting Started with PyTorch Image Models (timm): A Practitioner’s Guide]] #Timm
+ [[https://nlpoverview.com/#1][Modern Deep Learning Techniques Applied to Natural Language Processing]] #NLP
+ [[https://szeliski.org/Book/][Computer Vision: Algorithms and Applications, 2nd ed.]] #ComputerVision
+ [[https://twitter.com/omarsar0/status/1490276912601653248?s=20&t=-YwF6XNsPySPfoVGbFNR6Q][Graph neural networks resources]] #GNNs
+ [[https://uibakery.io/regex-library][UI Bakery RegEx Library]] #ExpresionesRegulares
 
** Enero 2022

+ [[https://keras.io/examples/keras_recipes/sample_size_estimate/?linkId=8029068][Estimating required sample size for model training]] #SampleSize #AP2122
+ [[https://academic.oup.com/femsre/article/45/4/fuaa062/6006878][Advances and opportunities in image analysis of bacterial cells and communities]] #ImageAnalysis #CarmenLozano 
+ [[https://wttech.blog/blog/2021/a-guide-to-model-calibration/][A guide to model calibration]] #Calibration
+ [[https://benanne.github.io/2022/01/31/diffusion.html][Diffusion models are autoencoders]] #DiffusionModels
+ [[https://arxiv.org/pdf/2110.06283.pdf][A Good Representation Detects Noisy Labels]] #NoiseLabels #OPTRetina
+ [[https://arxiv.org/abs/2104.14294][Emerging Properties in Self-Supervised Vision Transformers]] #Transformers #SelfSupervisedLearning
+ [[https://arxiv.org/pdf/2201.09873v1.pdf#page=33&zoom=100,64,377][Transformers in Medical Imaging: A Survey]] #Transformers #MedicalImaging
+ [[https://github.com/paperswithcode/releasing-research-code][Tips for Publishing Research Code]] #Reproducibility
+ [[https://arxiv.org/abs/2103.13559][Rethinking Self-Supervised Learning: Small is Beautiful]] #SelfSupervisedLearning #SmallData
+ [[https://arxiv.org/pdf/2201.10728.pdf][Training Vision Transformers with Only 2040 Images]] #Transformers #SelfSupervisedLearning #SmallData
+ [[https://www.tandfonline.com/doi/full/10.1080/00031305.2017.1375989][Data Organization in Spreadsheets]] #Spreadsheets #Data
+ [[https://pythonspeed.com/articles/vectorization-python/][How vectorization speeds up your Python code]] #Python #Vectorization
+ [[https://www.nature.com/articles/s41591-021-01614-0][AI in health and medicine]] #AI #Medicine
+ [[https://ai.facebook.com/blog/the-first-high-performance-self-supervised-algorithm-that-works-for-speech-vision-and-text][The first high-performance self-supervised algorithm that works for speech, vision, and text]] #SelfSupervisedLearning #MultiModality #Vision #Text #Sound
+ [[https://github.com/huggingface/transformers/tree/master/examples/research_projects/robust-speech-event#important-dates][Robust Speech Challange]] #SpeechRecognition #HuggingFace #Gobierno
+ [[https://ai.googleblog.com/2021/10/self-supervised-learning-advances.html][Self-Supervised Learning Advances Medical Image Classification]] #SelfSupervisedLearning #ImageClassification
+ [[https://ojs.aaai.org/index.php/aimagazine/article/view/18140][Deep Learning for Recommender Systems: A Netflix Case Study]] #RecommendationSystems
+ [[https://www.youtube.com/watch?v=8owQBFAHw7E][Intro to graph neural networks (ML Tech Talks)]] #GNN
+ [[https://scikit-learn.org/stable/modules/outlier_detection.html][2.7. Novelty and Outlier Detection]] #AnomalyDetection #Sklearn
+ [[https://poatek.com/2021/12/20/mlops-a-complete-and-hands-on-introduction-part-1/][MLOPS: A COMPLETE AND HANDS-ON INTRODUCTION]] [[https://poatek.com/2021/12/29/mlops-a-complete-and-hands-on-introduction-part-2/][Part2]] #MLOPS
+ [[https://queue.acm.org/detail.cfm?id=3511299][Interpretable Machine Learning]] #Interpretability
+ [[https://arxiv.org/pdf/2201.05867.pdf][Transferability in Deep Learning: A Survey]] #TransferLearning 
+ [[https://ai.googleblog.com/2022/01/introducing-stylex-new-approach-for.html][Introducing StylEx: A New Approach for Visual Explanation of Classifiers]] #Explainability
+ [[https://arxiv.org/abs/2201.02177][Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets]] #SmallDatasets #Overfitting
+ [[https://ffcv.io/][FFCV: an Optimized Data Pipeline for Accelerating ML Training]] #Fast #LibraryTraining
+ [[https://huggingface.co/tasks][HuggingFace Tasks]]
+ [[https://towardsdatascience.com/transformers-explained-visually-not-just-how-but-why-they-work-so-well-d840bd61a9d3][Transformers Explained Visually — Not Just How, but Why They Work So Well]] #Transformers
+ [[https://arxiv.org/pdf/2201.03898.pdf][An Introduction to AutoEncoders]] #AutoEncoders
+ [[https://github.com/Vaibhavs10/ml-with-audio][Hugging Face Machine Learning for Audio Study Group]] #Audio
+ [[https://arxiv.org/abs/1811.12808][Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning]] #ModelEvaluation #DatasetSplit
+ [[https://arxiv.org/abs/2110.06207][Open-Set Recognition: A Good Closed-Set Classifier is All You Need]] #OpenSetRecognition #
+ [[https://arxiv.org/abs/2201.02028][A Light in the Dark: Deep Learning Practices for Industrial Computer Vision]] #ComputerVision #Industry
+ [[https://machinelearningmastery.com/anomaly-detection-with-isolation-forest-and-kernel-density-estimation/?utm_source=drip&utm_medium=email&utm_campaign=Python+debugging+tools&utm_content=Python+debugging+tools][Anomaly Detection with Isolation Forest and Kernel Density Estimation]] #AnnomalyDetection
+ [[https://hci.stanford.edu/publications/2021/FnT_AuditingAlgorithms.pdf][Auditing Algorithms Understanding Algorithmic Systems from the Outside In]] #Ethics #Audits #Bikolabs
+ [[https://aditya-sengupta.github.io/coding/2022/01/13/wordle.html][Maximising Differential Entropy to Solve Wordle]] #Algorithms
+ [[https://huggingface.co/blog][Huggingface blog]] #HuggingFace
+ [[https://keras.io/examples/vision/vit_small_ds/][Train a Vision Transformer on small datasets]] #Transformers #SmallDataset
+ [[https://huggingface.co/blog/wav2vec2-with-ngram][Boosting Wav2Vec2 with n-grams in 🤗 Transformers]] #Audio #GobiernoRioja
+ [[https://arxiv.org/abs/2201.04182][HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning]] #FewShotLearning
+ [[https://github.com/gradio-app/awesome-demos][Awesome Gradio Demos]] #Gradio #Demos
+ [[https://arxiv.org/abs/2201.03529][Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning]] #TransferLearning
+ [[https://arxiv.org/pdf/2201.03545.pdf][A ConvNet for the 2020s]] #ComputerVision #CNNs
+ [[https://tmabraham.github.io/blog/gradio_hf_spaces_tutorial][Gradio + HuggingFace Spaces: A Tutorial]] #HuggingFace #Gradio
+ [[https://arxiv.org/pdf/2106.01834.pdf][Continual Learning in Deep Networks: an Analysis of the Last Layer]] #ContinualLearning
+ [[https://elvissaravia.substack.com/p/my-recommendations-for-getting-started][https://elvissaravia.substack.com/p/my-recommendations-for-getting-started]] #NLP
+ [[https://click.convertkit-mail.com/68uv053r88i8h3gxnxu9/6qhehoupodek47io/aHR0cHM6Ly9sZWFybm9wZW5jdi5jb20vdHJhbnNmZXItbGVhcm5pbmctZm9yLW1lZGljYWwtaW1hZ2VzLw==][transfer learning for medical imaging]] #TransferLearning #MedicalImaging
+ [[https://github.com/heejkoo/Awesome-Diffusion-Models][Diffusion Models and Score-matching Models]] #DiffusionModels
+ [[https://docs.fast.ai/distributed.html][Distributed Learning FastAI]] #DistributedLearning #FastAI
+ [[https://arxiv.org/abs/2106.13112][VOLO: Vision Outlooker for Visual Recognition]] #Transformer #ImageClassification
+ [[https://medmnist.com/][MedMNIST v2: A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification]] #Datasets #ImageClassification #Master
+ [[https://arxiv.org/abs/2110.11334][Generalized Out-of-Distribution Detection: A Survey]] #OutOfDistribution #AnomalyDetection #Survey
+ [[https://arxiv.org/abs/2112.15210][Persformer: A Transformer Architecture for Topological Machine Learning]] #TDA #Transformers #Interpretability
+ [[https://youtu.be/kQ09eg513Nc][AugMax explained]] #DataAugmentation
+ [[http://jalammar.github.io/illustrated-retrieval-transformer/][The Illustrated Retrieval Transformer]] #Transformer #LanguageModel
+ [[https://rockt.github.io/2018/04/30/einsum][EINSUM IS ALL YOU NEED - EINSTEIN SUMMATION IN DEEP LEARNING]] #MatrixOperations
+ [[https://pytorch.org/tutorials/beginner/nn_tutorial.html][WHAT IS TORCH.NN REALLY?]] #Pytorch #Tutorial
+ [[https://iterative-refinement.github.io/palette/][Palette: Image-to-Image Diffusion Models]] #DIffusionModels #ImageTranslation
+ [[https://arxiv.org/abs/2110.14711][A Survey of Self-Supervised and Few-Shot Object Detection]] #ObjectDetection #FewShotLearning #Survey
+ [[http://ai.googleblog.com/2021/12/training-machine-learning-models-more.html][Training Machine Learning Models More Efficiently with Dataset Distillation]] #DatasetDistillation  #Sevilla 
+ [[https://www.nature.com/articles/nature10836][The case for open code]] #OpenScience
 
* Lecturas del year 2021

** Diciembre 2021

+ [[https://youtu.be/oYUkAvhBNsg][Active Learning]] #ActiveLearning
+ [[https://transformer-circuits.pub/2021/framework/index.html][A Mathematical Framework for Transformer Circuits]] #Transformers
+ [[https://arthurdouillard.com/deepcourse/][Deep Learning course for Vision]] #ComputerVision #DeepLearning #Course
+ [[https://arxiv.org/pdf/2005.10876.pdf][Unsupervised Domain Adaptation in Semantic Segmentation: a Review]] #DomainShift #SemanticSegmentation
+ [[https://www.youtube.com/watch?v=ihkylUbqFMI&authuser=0][ADL4CV:DV - Semi-Supervised Learning]] #SemiSupervisedLearning
+ [[http://www.r2d3.us/][A VISUAL INTRODUCTION TO MACHINE LEARNING]]
+ [[https://www.bates.edu/mathematics/resources/latex-manual/][The Bates LaTeX Manual]] #Latex
+ [[https://www.youtube.com/playlist?list=PLo2EIpI_JMQvcXKx5RFReyg6Qd2UICAif][Hugging Face Course Event]] #HuggingFace #NLP #Course
+ [[https://arxiv.org/pdf/2111.09453.pdf][RoBERTuito: a pre-trained language model for social media text in Spanish]] #NLP #Spanish
+ [[https://colinraffel.com/blog/a-call-to-build-models-like-we-build-open-source-software.html][A Call to Build Models Like We Build Open-Source Software]] #Reproducibility #MLOPs
+ [[https://arxiv.org/pdf/2111.11646.pdf][CytoImageNet: A large-scale pretraining dataset for bioimage transfer learning]] #BioImage #Dataset
+ [[https://hal.inria.fr/hal-03427242/document][Scientific Visualization: Python + Matplotlib]] #Visualization
+ [[https://ai.google.com/research/NaturalQuestions][Open Domain Question Answering]] #NLP #QuestionAnswering
+ [[https://www.microsoft.com/en-us/research/blog/three-mysteries-in-deep-learning-ensemble-knowledge-distillation-and-self-distillation/][Three mysteries in deep learning: Ensemble, knowledge distillation, and self-distillation]] #Ensemble #Distillation
+ [[https://arxiv.org/abs/2105.06224][LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment]] #CellDetection #Athento
+ [[https://arxiv.org/abs/2112.00725][Extrapolating from a Single Image to a Thousand Classes using Distillation]] #Ðistillation
+ [[https://deepmind.com/blog/article/language-modelling-at-scale][Language modelling at scale: Gopher, ethical considerations, and retrieval]] #LanguageModel #NLP
+ [[https://huggingface.co/blog/data-measurements-tool][Introducing the 🤗 Data Measurements Tool: an Interactive Tool for Looking at Datasets]] #Datasets
+ [[https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/file/757b505cfd34c64c85ca5b5690ee5293-Paper-round2.pdf][Are We Learning Yet? A Meta-Review of Evaluation Failures Across Machine Learning]] #MachineLearning #Metrics #Failures
+ [[https://www.thelancet.com/journals/landig/article/PIIS2589-7500(21)00208-9/fulltext][The false hope of current approaches to explainable artificial intelligence in health care]] #Explainability #Healthcare
+ [[https://www.sciencedirect.com/science/article/pii/S0895435621003541?dgcid=author][Believing in black boxes: machine learning for healthcare does not need explainability to be evidence-based]] #Explainability #Healthcare
+ [[https://ai.googleblog.com/2021/10/practical-differentially-private.html][Practical Differentially Private Clustering]] #DifferentialPrivacy #Clustering

** Noviembre 2021

+ [[https://ai.googleblog.com/2021/11/model-ensembles-are-faster-than-you.html][Model Ensembles Are Faster Than You Think]] #Ensemble
+ [[https://albumentations.ai/docs/autoalbument/introduction/][AutoAlbument]] #DataAugmentation
+ [[https://arxiv.org/pdf/2111.05464.pdf][Are Transformers More Robust Than CNNs?]] #Transformers #CNNs #Robustness
+ [[https://link.springer.com/content/pdf/10.1007/s13748-021-00239-1.pdf][Deep limitations? Examining expert disagreement over deep learning]] #DeepLearning #AGI
+ [[https://theaisummer.com/transformers-computer-vision/][Transformers in computer vision: ViT architectures, tips, tricks and improvements]] #Transformers #ComputerVision

** Octubre 2021

+ [[https://arxiv.org/pdf/2108.00114.pdf][On The State of Data In Computer Vision: Human Annotations Remain Indispensable for Developing Deep Learning Models]] #Datasets
+ [[https://thegradient.pub/reflections-on-foundation-models/][Reflections on Foundation Models]]
+ [[https://www.nature.com/articles/s41592-021-01284-3.pdf][Avoiding a replication crisis in deep-learningbased bioimage analysis]] #DeepLearning #Microscope #Metrics
+ [[https://ai.googleblog.com/2021/10/baselines-for-uncertainty-and.html][Baselines for Uncertainty and Robustness in Deep Learning]] #Robustness
+ [[https://www.assemblyai.com/blog/deepspeech-for-dummies-a-tutorial-and-overview-part-1/][DeepSpeech for Dummies - A Tutorial and Overview]] #Audio #Gobierno
+ [[https://arxiv.org/pdf/2110.05025.pdf][Self-supervised Learning is More Robust to Dataset Imbalance]] #SelfSupervisedLearning #DatasetImbalance #OPTRetina
+ [[https://www.ujaen.es/centros/ceatic/noticias/ya-puedes-ver-el-video-de-la-charla-de-ana-freire-de-ayer][STOP: Estudiando problemas mentales en redes sociales mediante Inteligencia Artificial]]
+ [[https://arxiv.org/pdf/2106.10860.pdf][Multiplying Matrices Without Multiplying]] #MatrixMultiplication #DeepLearning
+ [[https://ai.googleblog.com/2021/10/self-supervised-learning-advances.html][Self-Supervised Learning Advances Medical Image Classification]] #SelfSupervisedLearning #MedicalImaging [[https://arxiv.org/pdf/2101.05224.pdf][Paper]]
+ [[https://www.cs.usask.ca/faculty/stavness/cvppa2021/papers/Fei_13.pdf][Enlisting 3D Crop Models and GANs for More Data Efficient and Generalizable Fruit Detection]] #CycleGAN #OutOfDomain
+ [[https://arxiv.org/pdf/2106.05210.pdf][Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation]] #VideoSegmentation
+ [[https://faculty.washington.edu/ebender/2021_575/][ Societal Impacts of NLP]] #NLP #Ethics
+ [[https://arxiv.org/pdf/2104.03829v1.pdf][Does Your Dermatology Classifier Know What It Doesn’t Know? Detecting the Long-Tail of Unseen Conditions]] #OutlierDetection #OPTRetina
+ [[https://openreview.net/forum?id=TVHS5Y4dNvM][Patches Are All You Need?]] #CNNs #Classification
+ [[https://www.jmir.org/2021/7/e27822][Application of an Anomaly Detection Model to Screen for Ocular Diseases Using Color Retinal Fundus Images: Design and Evaluation Study]] #AnomalyDetection #Retina
+ [[https://machinelearningmastery.com/one-class-classification-algorithms/][One-Class Classification Algorithms for Imbalanced Datasets]] #OneClassClassification
+ [[https://arxiv.org/pdf/1708.02750.pdf][Extreme clicking for efficient object annotation]] #ObjectDetection #Annotation
+ [[https://ai.googleblog.com/2021/09/revisiting-mask-head-architectures-for.html][Revisiting Mask-Head Architectures for Novel Class Instance Segmentation]] #SemanticSegmentation
+ [[https://www.nature.com/articles/s41592-021-01262-9.epdf?sharing_token=gFbjdF-nflWTb11ulG7OwdRgN0jAjWel9jnR3ZoTv0NeCGAajxJJG9eNeKTuUDwD-rhKcp8lM5VPvscQ0aFZy_yWdNcPyVNt0r-ShB4cf_G0kZMRVgOoeQL6iHxScPIXcfKgBxgePB7jIMAk0K2zQk6TrnarJenPJemoyfnA4ts%3D][DeepImageJ: A user-friendly environment to run deep learning models in ImageJ]] #Adrián #ImageJ
+ [[https://uwspace.uwaterloo.ca/handle/10012/17103][Learning From Almost No Data]] #Sevilla #DataDistillation
+ [[https://arxiv.org/abs/2110.00476][ResNet strikes back: An improved training procedure in timm]] #ImageClassification #TrainingTricks
+ [[https://keras.io/examples/vision/handwriting_recognition/][Handwriting recognition]] #HandwritingRecognition #IER

** Septiembre 2021
 
+ [[https://arxiv.org/pdf/2108.10520.pdf][Improving Object Detection by Label Assignment Distillation]] #ObjectDetection #Distillation
+ [[https://ai.googleblog.com/2021/09/revisiting-mask-head-architectures-for.html][Revisiting Mask-Head Architectures for Novel Class Instance Segmentation]] #InstanceSegmentation
+ [[https://github.com/obss/sahi][SAHI: A vision library for large-scale object detection & instance segmentation]] #ObjectDetection
+ [[https://arxiv.org/pdf/2012.05463.pdf][Investigating Bias in Image Classification using Model Explanations]] #Bias #Interpretability
+ [[https://arxiv.org/pdf/1711.11279.pdf][Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)]] #Interpretability
+ [[https://github.com/unica-mlsec/mlsec][Machine Learning Security / Adversarial Machine Learning]] #MachineLearning #Security
+ [[https://arxiv.org/abs/2109.10852][Pix2seq: A Language Modeling Framework for Object Detection]] #ObjectDetection
+ [[https://blog.openmined.org/private-ai-machine-learning-on-encrypted-data/][PRIVATE AI: MACHINE LEARNING ON ENCRYPTED DATA]] #Privacy
+ [[https://www.youtube.com/watch?v=jiftCAhOYQA][Hugging Face Infinity]] #HuggingFace #Inference #RealTime
+ [[https://arxiv.org/pdf/1910.02551.pdf][Soft-Label Dataset Distillation and Text Dataset Distillation]] #Distillation #Sevilla
+ [[https://arxiv.org/pdf/1811.10959.pdf][Dataset Distillation]] #Distillation #Sevilla
+ [[https://arxiv.org/pdf/2106.09018v2.pdf][End-to-End Semi-Supervised Object Detection with Soft Teacher]] #SemiSupervisedLearning #ObjectDetection
+ [[https://ai.googleblog.com/2021/09/toward-fast-and-accurate-neural.html][Toward Fast and Accurate Neural Networks for Image Recognition]] #ImageClassification
+ [[https://medium.com/marionete/tinyml-models-whats-happening-behind-the-scenes-5e61d1555be9][TinyML models — what happens behind the scenes]] #CompactNetworks
+ [[https://calmcode.io/altair/introduction.html][Altair]] #DataVisualization
+ [[https://www.youtube.com/watch?v=IC4qZE5Wljs][Training StyleGAN2 ADA PyTorch Images with Low GPU Memory NVIDIA]] #GAN
+ [[https://lilianweng.github.io/lil-log/2021/05/31/contrastive-representation-learning.html][Contrastive Representation Learning]] #ContrastiveLearning
+ [[https://www.novetta.com/2021/03/learning-rate/][Methods for Automating Learning Rate Finders]] #LearningRate #FastAI [[https://docs.fast.ai/callback.schedule.html#Suggestion-Methods][Suggestion Methods]]
+ [[https://bowenc0221.github.io/maskformer/][Per-Pixel Classification is NOT All You Need for Semantic Segmentation]] #SemanticSegmentation
+ [[https://imagingtext.github.io/cibook.pdf][Computational Imaging]] #Imaging
+ [[https://learnopencv.com/introduction-to-intel-openvino-toolkit/][Introduction to Intel OpenVINO Toolkit]] #Quantization
+ [[https://huggingface.co/datasets][HuggingFace Datasets]] #Datasets #NLP
+ [[https://readthedocs.org/][Read the Docs]] #Documentation #SemTorch
+ [[https://towardsdatascience.com/why-you-should-not-rely-on-t-sne-umap-or-trimap-f8f5dc333e59][Why you should not rely on t-SNE, UMAP or TriMAP]] #DimensionalityReduction #PaCMAP
+ [[https://madewithml.com/courses/mlops/objective/][Made with ML]] #MLOps
+ [[https://pytorch.org/blog/torchvision-mobilenet-v3-implementation/][Everything you need to know about TorchVision’s MobileNetV3 implementation]] #CompactNetworks
+ [[https://arxiv.org/pdf/2103.10292.pdf][How I failed machine learning in medical imaging - shortcomings and recommendations]] #MedicalImaging
+ [[https://arxiv.org/abs/2107.136710][Deeper Learning By Doing: Integrating Hands-On Research Projects Into a Machine Learning Course]] #MachineLearning #Teaching
+ [[https://youtu.be/w6Pw4MOzMuo][Ver "ICLR 2021 Keynote - "Geometric Deep Learning: The Erlangen Programme of ML" - M Bronstein" en YouTube]] #GeometricDeepLearning #GraphNeuralNetworks
+ [[https://t.co/iZFbEm0F0K?amp=1][The Annotated DETR]] #ObjectDetection #Transformers
+ [[https://ai.facebook.com/blog/self-supervised-learning-the-dark-matter-of-intelligence/][Self-supervised learning: The dark matter of intelligence]] #
+ [[https://analyticsindiamag.com/all-the-free-ml-ai-courses-launched-at-google-i-o/][All The Free ML/AI Courses Launched At Google I/O]] #Courses #Tensorflow #Edge
+ [[https://www.sciencedirect.com/science/article/pii/S0065245816300572][A Systematic Approach to Generation of New Ideas for PhD Research in Computing - ScienceDirect]] #Thesis #Ideas
+ [[https://arxiv.org/pdf/2108.02497.pdf][How to avoid machine learning pitfalls: a guide for academic researchers]] #Recommendations
+ [[https://developer.nvidia.com/blog/deciphering-ancient-texts-with-ai/?mkt_tok=MTU2LU9GTi03NDIAAAF-2uW9LTpK75b2F0K4DF81KwECCnIzCG4fGZLdh0toV48cU9tKeFUjcfUtDpKhL-meRBCI5dAx0cYAKL6t2d6UOmYg-hMzxaNhPVCh-ECtAeFXAo0][Deciphering Ancient Texts with AI]] #IER #AncientDocuments #OCR
+ [[https://arxiv.org/pdf/2007.15745.pdf][On hyperparameter optimization of machine learning algorithms: Theory and practice]] #HyperparameterTuning #Survey
+ [[https://cacm.acm.org/magazines/2021/7/253464-deep-learning-for-ai/fulltext][Deep Learning for AI]] #DeepLearning #Challenges
+ [[https://arxiv.org/pdf/2009.05673.pdf][Applications of Deep Neural Networks with Keras]] #Book #Keras
+ [[https://arxiv.org/pdf/2107.05407.pdf][PonderNet: Learning to Ponder]] #Pondering
+ [[https://arxiv.org/pdf/2108.06883v2.pdfhttps://arxiv.org/pdf/2108.06883v2.pdf][CarveMix: A Simple Data Augmentation Method for Brain Lesion Segmentation]] #DataAugmentation #SemanticSegmentation
+ [[http://proceedings.mlr.press/v137/biderman20a/biderman20a.pdf][Pitfalls in Machine Learning Research: Reexamining the Development Cycle]] #MachineLearning #Recommendations
+ [[https://github.com/qanastek/HugsVision][HugsVision]] #ComputerVision #Transformers
+ [[https://l7.curtisnorthcutt.com/confident-learning][An Introduction to Confident Learning: Finding and Learning with Label Errors in Datasets]] #ConfidentLearning
+ [[https://calmcode.io/bad-labels][Bad Labels]] #BadLabels #ActiveAnnotation #OPTRetina [[https://github.com/cgnorthcutt/cleanlab][CleanLAB]]
+ [[https://arxiv.org/pdf/2109.00574.pdf][Active label cleaning: Improving dataset quality under resource constraints]] #Annotation #MedicalImaging #OPTRetina
+ [[https://tezansahu.medium.com/fundamentals-of-mlops-part-1-a-gentle-introduction-to-mlops-1b184d2c32a8][Fundamentals of MLOps | A Gentle Introduction to MLOps]] [[https://tezansahu.medium.com/fundamentals-of-mlops-part-1-a-gentle-introduction-to-mlops-1b184d2c32a8][Parte 1]] [[https://tezansahu.medium.com/fundamentals-of-mlops-part-2-data-model-management-with-dvc-6be2ad284ec4][Parte 2]] [[https://tezansahu.medium.com/fundamentals-of-mlops-part-3-ml-experimentation-using-pycaret-747f14e4c28d][Parte 3]] [[https://tezansahu.medium.com/fundamentals-of-mlops-part-4-tracking-with-mlflow-deployment-with-fastapi-61614115436][Parte 4]]
+ [[https://distill.pub/2021/gnn-intro/][A Gentle Introduction to Graph Neural Networks]] #GraphNeuralNetworks

** Agosto 2021

+ [[https://arxiv.org/pdf/2009.05673.pdf][Applications of Deep Neural Networks with Keras]]
+ [[https://cacm.acm.org/magazines/2021/7/253464-deep-learning-for-ai/fulltext][Deep Learning for AI]] #Challenges #GodFathers
+ [[https://docs.manim.community/en/stable/index.html][Manim Community Overview]] #Visualization #Animation
+ [[https://arxiv.org/pdf/2107.10356.pdf][Reading Race: AI Recognizes Patient’s Racial Identity In Medical Images]] #Ethics #MedicalAI
+ [[https://lukeoakdenrayner.wordpress.com/2021/08/02/ai-has-the-worst-superpower-medical-racism/][AI has the worst superpower… medical racism]] #Ethics #MedicalAI
+ [[https://martinfowler.com/articles/practical-test-pyramid.html][Practical Test Pyramid]] #DDD #TDD #Tests

** Julio 2021

+ [[https://ai.googleblog.com/2021/06/data-cascades-in-machine-learning.html][Data Cascades in Machine Learning]] #Data
+ [[https://openai.com/blog/triton/][Introducing Triton: Open-Source GPU Programming for Neural Networks]] #GPUs #CUDA
+ [[https://theaisummer.com/self-supervised-representation-learning-computer-vision/][Grokking self-supervised (representation) learning: how it works in computer vision and why]] #SelfSupervisedLearning
+ [[https://ai.facebook.com/blog/augly-a-new-data-augmentation-library-to-help-build-more-robust-ai-models/][AugLy: A new data augmentation library to help build more robust AI models]] #DataAugmentation
+ [[https://arxiv.org/pdf/2103.10292.pdf][How I failed machine learning in medical imaging - shortcomings and recommendations]] #MedicalImaging
+ [[https://www.frontiersin.org/articles/10.3389/frai.2021.681108/full][A Survey of Topological Machine Learning Methods]] #TDA
+ [[https://github.com/google-research/robustness_metrics][Robustness Metrics]]
+ [[https://arxiv.org/pdf/2107.04902.pdf][Industry and Academic Research in Computer Vision]] #ComputerVision
+ [[https://dl.acm.org/doi/10.1145/3442188.3445922][On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?]] #NLP #Ethics
+ [[https://arxiv.org/abs/2106.10270][How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers]] #Transformers #Tricks
+ [[https://arxiv.org/pdf/1912.05283.pdf][Identifying Mislabeled Instances in Classification Datasets]] #DataCleaning
+ [[https://www.blog.pythonlibrary.org/2021/05/27/pyinstaller-how-to-turn-your-python-code-into-an-exe-on-windows/][PyInstaller – How to Turn Your Python Code into an Exe on Windows]] #Pyinstaller
+ [[https://arxiv.org/pdf/1405.4097.pdf][A preliminary study of Croatian Language Syllable Networks]] #NLP #Arista
+ [[https://papers.nips.cc/paper/2018/file/c1fea270c48e8079d8ddf7d06d26ab52-Paper.pdf][Realistic Evaluation of Deep Semi-Supervised Learning Algorithms]] #SemiSupervisedLearning
+ [[https://www.nature.com/articles/s41467-020-17478-w.pdf][Causality matters in medical imaging]] #Causality
+ [[https://youtu.be/iMDawBTYQGU][Computer Vision and the Global Goals]]

** Junio 2021

+ [[https://arxiv.org/pdf/2012.02312.pdf][ReMix Training for Calibrated Imbalanced Deep Learning]] #ImbalanceData
+ [[https://arxiv.org/pdf/2106.04732.pdf][AdaMatch: A Unified Approach to Semi-SupervisedLearning and Domain Adaptation]] #SemiSupervisedLearning #DomainAdaption
+ [[https://arxiv.org/pdf/1710.05381.pdf][A systematic study of the class imbalance problemin convolutional neural networks]] #DataImbalance
+ [[https://journalofbigdata.springeropen.com/articles/10.1186/s40537-019-0192-5][Survey on deep learning with class imbalance]] #DataImbalance
+ [[https://ohmeow.com/posts/2021/06/03/ajtfb-chapter-5.html][A Journey Through Fastbook (AJTFB) - Chapter 5]] #FastAI
+ [[https://www.frontiersin.org/articles/10.3389/frai.2021.681108/full][A Survey of Topological Machine Learning Methods]] #TDA
+ [[https://www.nature.com/articles/s41557-021-00716-z][Best practices in machine learning for chemistry]]
+ [[https://nathanhubens.github.io/fasterai/][Fasterai: A library to make smaller and faster neural networks]] #Pruning #FastAI

** Mayo 2021

+ [[https://blog.tensorflow.org/2021/05/next-generation-pose-detection-with-movenet-and-tensorflowjs.html][Next-Generation Pose Detection with MoveNet and TensorFlow.js]] #PoseDetection #Skeletons #RobertoMarani
+ [[https://www.youtube.com/watch?v=727WIwTTNn8&t=8s][Taller MLOps: desplegando servicios en producción]] #MLOps
+ [[https://www.kaggle.com/yassinealouini/all-the-segmentation-metrics][All the segmentation metrics!]] #Segmentation #Metrics
+ [[https://sociam.github.io/saap-workshop/resources/01_Ayling_Zhou_Chapman_final.pdf][Algorithmic Accountability and the Role ofProvenance]] 
+ [[https://www.cognitivefactory.fr/fastaidocs][FastAI concepts]] #FastAI
+ [[https://colab.research.google.com/github/fepegar/torchio-notebooks/blob/main/notebooks/TorchIO_MONAI_PyTorch_Lightning.ipynb#scrollTo=GMI3YJNgCDjy][Medical image segmentation with TorchIO, MONAI & PyTorch Lightning]] #Segmentation #3D
+ [[https://octo.github.com/projects/flat-data][Flat Data]] #MLOps
+ [[https://www.youtube.com/watch?v=5F5LlmO10AM][Challenges of Advanced AutoML - Determined AI]] #AutoML
+ [[https://slideslive.com/38938406/the-infonce-loss-in-selfsupervised-learning][The InfoNCE loss in self-supervised learning ]] #SelfSupervisedLearning
+ [[https://www.biorxiv.org/content/10.1101/2021.03.27.437348v1][Measuring hidden phenotype: Quantifying the shape of barley seeds using the Euler Characteristic Transform]] #PlantPhenotyping #TDA
+ [[https://arxiv.org/pdf/2103.11251.pdf][Interpretable Machine Learning: FundamentalPrinciples and 10 Grand Challenges]] #Interpretability
+ [[https://github.com/craffel/dl3d-seminar][(Deep) Learning with Limited Labeled Data (DL3D)]] #SemiSupervisedLearning
+ [[https://arxiv.org/abs/2103.06326][S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning]] #SelfSupervision #ReinforcementLearning
+ [[https://arxiv.org/pdf/2103.10697.pdf][ConViT: Improving Vision Transformerswith Soft Convolutional Inductive Biases]] #Transformers #ImageClassification
+ [[https://arxiv.org/pdf/2103.10270.pdf][Requirement Engineering Challengesfor AI-intense Systems Development]] #HumanCentered #Requirements
+ [[https://arxiv.org/pdf/2105.03322.pdf][Are Pre-trained Convolutions Better than Pre-trained Transformers?]] #Convolutions #Transformers #TransferLearning #NLP
+ [[https://novetta.github.io/adaptnlp/][A high level framework and library for running, training, and deploying state-of-the-art Natural Language Processing (NLP) models for end to end tasks]] #NLP #FastAI
+ [[https://www.researchgate.net/publication/340438092_Human-centered_Explainable_AI_Towards_a_Reflective_Sociotechnical_Approach][Human-centered Explainable AI: Towards a Reflective Sociotechnical Approach]] #HumanCenteredAI
+ [[https://thegradient.pub/human-centered-explainable-ai/][Towards Human-Centered Explainable AI: the journey so far]] #HumanCenteredAI
+ [[https://arxiv.org/pdf/2105.03020.pdf][Structured dataset documentation: a datasheet for CheXpert]] #Datasets #Datasheet
+ [[https://keras.io/examples/vision/learnable_resizer/][Learning to Resize in Computer Vision]] #Resize #Tips
+ [[https://www.researchgate.net/publication/340438092_Human-centered_Explainable_AI_Towards_a_Reflective_Sociotechnical_Approach][Human-centered Explainable AI: Towards a Reflective Sociotechnical Approach]] #HumanCentered #Explanaible
+ [[https://thegradient.pub/machine-learning-ethics-and-open-source-licensing-2/][Machine Learning, Ethics, and Open Source Licensing (Part II/II)]] #Ethics #Licenses
+ [[https://fastai.github.io/timmdocs/RandAugment][RandAugment - Practical automated data augmentation with a reduced search space]] #DataAugmentation #RandAugment
+ [[https://wandb.ai/wandb_fc/pytorch-image-models/reports/Revisiting-ResNets-Improved-Training-and-Scaling-Strategies--Vmlldzo2NDE3NTM?galleryTag=][Revisiting ResNets: Improved Training and Scaling Strategies]] #Resnet #TrainingStrategies
+ [[https://arxiv.org/abs/2105.01601][MLP-Mixer: An all-MLP Architecture for Vision]] #ComputerVision #NLP
+ [[https://arxiv.org/pdf/2104.13478.pdf][Geometric Deep LearningGrids, Groups, Graphs,Geodesics, and Gauges]] #GeometricDeepLearning
+ [[https://www.sciencedirect.com/science/article/pii/S1350946218300119?via%3Dihub][Artificial intelligence in retina]] #Retina #OPTRetina

** Abril 2021

+ [[https://www.sscardapane.it/teaching/reproducibledl/][Reproducible Deep Learning]] #Reproducible #MLOps
+ [[https://thegradientpub.substack.com/p/machine-learning-ethics-and-open][Machine Learning, Ethics, and Open Source Licensing ]] #Ethics
+ [[https://yuliang.vision/pseudo_seg/][PseudoSeg: Designing Pseudo Labels for Semantic Segmentation]] #SemiSupervisedLearning #Segmentation
+ [[https://arxiv.org/pdf/2104.14294.pdf][Emerging Properties in Self-Supervised Vision Transformers]] #Transformers #SelfSupervisedLearning
+ [[https://www.youtube.com/watch?v=I0yrJz8uc5Q][Please Stop Doing "Explainable" ML - Cynthia Rudin]] #Interpretability
+ [[https://ex.pegg.io/][Explainable AI Cheat Sheet]] #Interpretability
+ [[https://arxiv.org/pdf/2104.13921.pdf][Zero-Shot Detection via Vision and Language Knowledge Distillation]] #ZeroShot #ObjectDetection
+ [[http://proceedings.mlr.press/v119/liang20a/liang20a.pdf][Do We Really Need to Access the Source Data? Source Hypothesis Transfer forUnsupervised Domain Adaptation]] #DomainShift #DomainTransfer
+ [[https://fullstackdeeplearning.com/spring2021/lecture-10/][Lecture 10: Testing & Explainability]] #Testing #Explainability
+ [[https://arxiv.org/pdf/2104.03602.pdf][SiT: Self-supervised vIsion Transformer]] #SelfSupervised #Transformers
+ [[https://umap-learn.readthedocs.io/en/latest/how_umap_works.html#adapting-to-real-world-data][How UMAP Works]] #UMAP
+ [[https://pair-code.github.io/understanding-umap/][Understanding UMAP]] #UMAP #DimensionalityReduction
+ [[https://www.youtube.com/watch?v=eS-OHAHOqU0&list=PLtBw6njQRU-rwp5__7C0oIVt26ZgjG9NI&index=11][MIT 6.S191: Taming Dataset Bias via Domain Adaptation]] #DomainAdaption #DomainShift
+ [[https://fullstackdeeplearning.com/spring2021/lecture-10/][Testing & Explainability]] #Testing #MLOPs

** Marzo 2021

+ [[https://avalanche.continualai.org/][Avalanche: an End-to-End Library for Continual Learning]] #ContinualLearning #Library #SEPARA
+ [[https://github.com/google/mediapy][Read/write/show images and videos in an IPython/Jupyter notebook]] #Visualization #Jupyter #Library
+ [[https://arxiv.org/pdf/2103.13318.pdf][Factors of Influence for Transfer Learning acrossDiverse Appearance Domains and Task Type]] #TransferLearning
+ [[https://stanford-cs329s.github.io/syllabus.html][CS 329S: Machine Learning Systems Design]] #MLOPS #Course
+ [[https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9361692][Hybrid Graph Convolutional Network forSemi-Supervised Retinal Image Classification]] #Retina #SemiSupervisedLearning
+ [[https://arxiv.org/pdf/2103.09108.pdf][Is it Enough to Optimize CNN Architectures on ImageNet?]] #ImageClassification 
+ [[https://neuraspike.com/blog/matplotlib-tutorial/][A Simple Walk-through with Matplotlib for Data Science]] #DataVisualization
+ [[http://people.maths.ox.ac.uk/nanda/cat/TDANotes.pdf][Computational Algebraic Topology Lecture Notes]] #AlgebraicTopology
+ [[https://modelcards.withgoogle.com/about][The value of a shared understanding of AI models]] #ModelCards #Datasets
+ [[https://petewarden.com/2018/05/28/why-you-need-to-improve-your-training-data-and-how-to-do-it/][Why you need to improve your training data, and how to do it]] #ProyectoSEPARA #Data
+ [[https://docs.google.com/presentation/d/1SSQE6sxMmiKx7KpK1bAQiSEAUvk0iMUHYzybrAgScJM/edit#slide=id.gc6f73a04f_0_0][ML in industry]] #ProyectoSEPARA
+ [[https://jax.readthedocs.io/en/latest/jax-101/index.html][Tutorial: JAX 101 ]] #JAX
+ [[https://fastai.github.io/timmdocs/models#My-dataset-doesn][My dataset doesn't consist of 3-channel images - what now? ]] #MultiSpectralImages #ProyectoSEPARA
+ [[https://arxiv.org/pdf/2103.01988.pdf][Self-supervised Pretraining of Visual Features in the Wild]] #SelfSupervisedLearning
+ [[https://github.com/visenger/awesome-mlops][Awesome MLOPs]] #MLOPS #Repository
+ [[https://ai.facebook.com/blog/self-supervised-learning-the-dark-matter-of-intelligence][Self-supervised learning: The dark matter of intelligence]] #SelfSupervisedLearning [[https://vissl.ai/][library]].
+ [[https://ai.facebook.com/blog/d2go-brings-detectron2-to-mobile/][D2Go brings Detectron2 to mobile]] #Detectron #Mobile #ProyectoSepara
+ [[https://www.quantitative-plant.org/][Quantitative Plant]] #Plants #Software #Repository
+ [[https://ruder.io/recent-advances-lm-fine-tuning/][Recent Advances in Language Model Fine-tuning]]


** Febrero 2021

+ [[https://arxiv.org/pdf/2102.12627.pdf][How to represent part-whole hierarchies in a neural network]] #RepresentationLearning
+ [[https://www.nature.com/articles/s41467-021-21187-3][AI-based mobile application tofight antibiotic resistance]] #Antibiotics #AntimicrobialResistance
+ [[https://arxiv.org/abs/2102.08602][LambdaNetworks: Modeling Long-Range Interactions Without Attention]] #ImageClassification
+ [[https://arxiv.org/abs/2102.09480][Unbiased Teacher for Semi-Supervised Object Detection]] #ObjectDetection #SemiSupervisedLearning
+ [[https://isaac-flath.github.io/fastblog/deep%20learning/2021/03/01/StyleGanComponents.html][Stylegan Components]] #StyleGAN
+ [[https://airctic.com/getting_started_mmdetection/][MMDetection and IceVision]] #MMDetection #Icevision
+ [[https://arxiv.org/pdf/2102.06171.pdf][High-Performance Large-Scale Image Recognition Without Normalization]] #ImageClassification
+ [[https://arxiv.org/pdf/2102.05644.pdf][Training Vision Transformers for Image Retrieval]] #Transformers #ImageRetrieval
+ [[https://sci-hub.se/10.1038/s41591-019-0508-1][Clinical-grade computational pathology using weakly supervised deep learning on whole  slide images]] #WeaklySupervised #Zaragoza
+ [[https://arxiv.org/abs/1703.10593][Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks]] #CycleGAN
+ [[https://arxiv.org/pdf/1902.05655.pdf][Going Deep in Medical Image Analysis:Concepts, Methods, Challenges and FutureDirections]] #MedicalImaging
+ [[https://www.youtube.com/watch?v=DbQNKdtoqUw&feature=youtu.be][Simple explanation of disentanglement ft. cute doggos & state-of-the-art work]] #Disentanglement
+ [[https://sgfin.github.io/2020/06/22/Induction-Intro/][Induction, Inductive Biases, and Infusing Knowledge into Learned Representations]] #RepresentationLearning
+ [[https://www.nature.com/articles/s41598-019-52737-x][Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks]] #DataAugmentation #Segmentation #CycleGAN
+ [[https://twitter.com/mervenoyann/status/1355907249038897156][NLP resources]] #NLP #Tutorials #Videos
+ [[https://sci-hub.se/10.1038/s41592-020-01008-z][nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation]] #Felix #Segmentation [[https://github.com/MIC-DKFZ/nnUNet][repository]]
+ [[https://news.mit.edu/2021/robust-artificial-intelligence-tools-predict-future-cancer-0128][Robust artificial intelligence tools to predict future cancer ]] #MedicalImaging #Robustness 
+ [[https://arxiv.org/abs/1809.04430][Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy]] #Segmenation #MedicalImaging
+ [[https://www.climatechange.ai/papers/neurips2020/74][Long-Range Seasonal Forecasting of 2m-Temperature with Machine Learning (Papers Track) ]] #ClimateChante #ML
+ [[https://www.paperswithcode.com/datasets][Datasets papers with code]] #Datasets
+ [[https://towardsdatascience.com/logicgamessolver-how-to-solve-logic-games-using-computer-vision-and-artificial-intelligence-1a4972e7e0be][LogicGamesSolver— How to solve logic games using Computer Vision and Artificial Intelligence]] #ComputerVision #Sudoku #IA
+ [[https://arxiv.org/pdf/2101.11605.pdf][Bottleneck Transformers for Visual Recognition]] #Transformers #CNN
+ [[https://missing.csail.mit.edu/][The Missing Semester of Your CS Education]] #ComputerScience #Lectures
+ [[https://machinelearningmastery.com/semi-supervised-generative-adversarial-network/][How to Implement a Semi-Supervised GAN (SGAN) From Scratch in Keras]] #SemiSupervisedLearning #GANs


** Enero 2021
 
+ [[https://arxiv.org/pdf/1511.06233.pdf][Towards Open Set Deep Networks]] #OpenSetRecognition
+ [[https://arxiv.org/pdf/1602.08465.pdf][Seq-NMS for Video Object Detection]] #VideoObjectDetection
+ [[https://www.microsoft.com/en-us/research/blog/vinvl-advancing-the-state-of-the-art-for-vision-language-models/][VinVL: Advancing the state of the art for vision-language models]] #VisualLanguageModels
+ [[https://www.mdpi.com/2079-9292/10/3/279/htm][A Comparative Analysis of Object Detection Metrics with a Companion Open-Source Toolkit]] #ObjectDetection #Metrics #Evaluation
+ [[https://arxiv.org/abs/2101.07571v1][An Improvement of Object Detection Performance using Multi-step Machine Learnings]] #ObjectDetection
+ [[https://stanford-cs329s.github.io/syllabus.html][CS 329S: Machine Learning Systems Design]] #MLOps
+ [[https://theaisummer.com/cnn-architectures/][Best deep CNN architectures and their principles: from AlexNet to EfficientNet]] #CNNs
+ [[https://github.com/daviddao/awful-ai][Awful AI]] #IA #Ethics #Misuses
+ [[https://arxiv.org/pdf/2010.04819v1.pdf][How Does Mixup Help With Robustness and Generalization?]] #MixUp #DataAugmentation
+ [[https://arxiv.org/abs/2101.06871][CheXtransfer: Performance and Parameter Efficiency of ImageNet Models for Chest X-Ray Interpretation]] #MedicalImaging #TransferLearning
+ [[https://huggingface.co/blog/zero-deepspeed-fairscale][Fit More and Train Faster With ZeRO via DeepSpeed and FairScale]] #NLP #Transformers #Efficiency
+ [[https://openreview.net/pdf?id=djwS0m4Ft_A][Evaluating the Disentanglement of Deep Generative Models through Manifold Topology]] #TDA
+ [[https://arxiv.org/pdf/2101.05224v1.pdf][Big Self-Supervised Models Advance Medical Image Classification]] #SelfSupervisedLearning #MedicalImaging
+ [[https://bdtechtalks.com/2021/01/11/concept-whitening-interpretable-neural-networks/][Deep learning doesn’t need to be a black box]] #Interpretability
+ [[https://analyticsindiamag.com/microsoft-research-unadversarial/][Microsoft Releases Unadversarial Examples: Designing Objects for Robust Vision – A Complete Hands-On Guide ]] #AdversarialExamples
+ [[https://arxiv.org/pdf/2011.08036.pdf][Scaled-YOLOv4: Scaling Cross Stage Partial Network]] #YOLO #ObjectDetection
+ [[https://keras.io/examples/][Keras Code examples]] #Keras #Samples
+ [[https://raevskymichail.medium.com/cowmask-data-augmentation-for-self-supervised-models-9623f99ef4bb][CowMask — Data Augmentation for Self-Supervised Models]] #SemiSupervisedLearning
+ [[https://arxiv.org/abs/1710.05381][A systematic study of the class imbalance problem in convolutional neural networks]] #CNNs #ImbalancedData
+ [[https://testdriven.io/guides/complete-python/][The Complete Python Development Guide]] #Python 
+ [[https://github.blog/2020-06-17-using-github-actions-for-mlops-data-science/][Using GitHub Actions for MLOps & Data Science ]] #MLOps
+ [[https://people.maths.ox.ac.uk/nanda/cat/][Computational Algebraic Topology]] #ComputationalAlgebraicTopology #Course #TDA
+ [[https://www.nature.com/articles/s41746-020-00376-2][Deep learning-enabled medical computer vision]] #MedicalImaging
+ [[https://arxiv.org/pdf/2101.01169.pdf][Transformers in Vision: A Survey]] #Transformers #ComputerVision
+ [[http://yacvid.hayko.at/index.php][Yet Another Computer Vision Index To Datasets (YACVID)]] #Datasets
+ [[https://arxiv.org/abs/2003.10580][Meta Pseudo Labels]] #SemiSupervisedLearning
+ [[https://dalex.drwhy.ai/python/][dalex: Responsible Machine Learning in Python]] #Explanability #Interpretability
+ [[https://machinelearningmastery.com/semi-supervised-learning-with-label-propagation/][Semi-Supervised Learning With Label Propagation]]  #SemiSupervisedLearning #LabelPropagation
+ [[https://openai.com/blog/clip/][CLIP: Connecting Text and Images]] #OpenAI #ImageClassification #SelfSupervisedLearning
+ [[https://d1.awsstatic.com/whitepapers/mlops-continuous-delivery-machine-learning-on-aws.pdf?did=wp_card][MLOps: Continuous Delivery forMachine Learning on AWS]] #MLOPs
+ [[https://arxiv.org/pdf/2012.14163v1.pdf][Multiple Document Datasets Pre-training ImprovesText Line Detection With Deep Neural Networks]] #Athento #DocumentAnalysis #HistoricalDocuments

* Lecturas del year 2020

** Diciembre 2020

+ [[https://arxiv.org/pdf/2012.12877.pdf][Training data-efficient image transformers& distillation through attention]] #Distillation #Transformers #ComputerVision
+ [[https://arxiv.org/abs/2012.07805][Extracting Training Data from Large Language Models]] #NLP
+ [[https://arxiv.org/abs/2012.07177][Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation]] #DataAugmentation #SemanticSegmentation
+ [[https://modestyachts.github.io/imagenet-testbed/][Measuring Robustness to Natural Distribution Shifts in Image Classification ]] #DomainShift #Robustness
+ [[https://epfml.github.io/attention-cnn/][Visualization of Self-Attention Maps in Vision]] #Interpretability #Attention
+ [[https://arxiv.org/abs/1906.03516][DiCENet: Dimension-wise Convolutions for Efficient Networks]] #EfficientNetworks #Mobile
+ [[https://arxiv.org/abs/2002.09437][Calibrating Deep Neural Networks using Focal Loss]] #Miscalibration #Loss
+ [[https://ethics-of-ai.mooc.fi/start][https://ethics-of-ai.mooc.fi/start]] #Mooc #Ethics
+ [[https://ogb.stanford.edu/][Open Graph Benchmark]] #Datasets #GraphNeuralNetworks #Benchmark
+ [[https://arxiv.org/pdf/2012.07421.pdf][Wilds: A Benchmark of in-the-Wild Distribution Shifts]] #DomainShift #Manuel [[https://t.co/bwOiG9R5Ct][Webpage]]
+ [[https://arxiv.org/pdf/2004.07780.pdf][Shortcut Learning in Deep Neural Networks]] #Robustness #Transferability #DomainShift
+ [[https://arxiv.org/pdf/2011.09903.pdf][Impact of Accuracy on Model Interpretations]] #Interpretability #LIME #SHAP #Mareas
+ [[GCTI-SN: Geometry-inspired chemical and tissue invariant stain normalization of microscopic medical images][GCTI-SN: Geometry-inspired chemical and tissue invariant stain normalization of microscopic medical images]] #ColourNormalisation #StyleTransfer
+ [[https://analyticsindiamag.com/onenet/][OneNet: Introduction to End-to-End One-Stage Object Detection ]] #ObjectDetection
+ [[https://arxiv.org/pdf/2004.08955.pdf][ResNeSt: Split-Attention Networks]] #ImageClassification
+ [[https://blog.tensorflow.org/2020/11/my-experience-with-tensorflow-quantum.html][My experience with TensorFlow Quantum]] #Tensorflow #QuantumComputing
+ [[https://twitter.com/PetarV_93/status/1306689702020382720][Resources Graph Neural Networks]] #GraphNeuralNetworks
+ [[https://arxiv.org/pdf/1912.12693.pdf][A Gentle Introduction to Deep Learning for Graphs]] #GraphNeuralNetworks
+ [[https://blog.einstein.ai/comatch-advancing-semi-supervised-learning-with-contrastive-graph-regularization/][CoMatch: Advancing Semi-supervised Learning with Contrastive Graph Regularization]] #SemiSupervisedLearning #ContrastiveRegularization
+ [[http://gabrielilharco.com/publications/EMNLP_2020_Tutorial__High_Performance_NLP.pdf][High Performance Natural Language Processing]] #NLP
+ [[https://github.blog/2020-11-20-nbdev-a-literate-programming-environment-that-democratizes-software-engineering-best-practices/][Nbdev: A literate programming environment that democratizes software engineering best practices]] #NBDev #JupyterNotebooks #FastAI
+ [[https://towardsdatascience.com/getting-started-with-giotto-learn-a-python-library-for-topological-machine-learning-451d88d2c4bc][Getting started with giotto-tda]] #TDA 
+ [[https://www.nature.com/articles/s41592-020-01008-z.epdf?sharing_token=4jS8WCio35M6tfgQUUXamtRgN0jAjWel9jnR3ZoTv0MPk71Wg6vREldiNjHEbU89_ehOOb_NLZNqil4VHQLygNjZAbd5f4rttCieNLf4e_cDouFUxnVsIw7jpYI0G0GhIxZRSNtNTx2Fihu-cMDbH-RlIsKJFlO08zK9a1yTtZk%3D][nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation]] #Segmentation #AutoML
+ [[https://arxiv.org/abs/2012.05628][As good as new. How to successfully recycle English GPT-2 to make models for other languages]] #NLP #GPT
+ [[https://arxiv.org/pdf/2011.13920.pdf][Unsupervised part representation by Flow Capsules]] #Capsules #SelfSupervisedLearning
+ [[https://colab.research.google.com/github/hirotomusiker/schwert_colab_data_storage/blob/master/notebook /Vision_Transformer_Tutorial.ipynb#scrollTo=J9lOBfezfPCX][Unofficial Walkthrough of Vision Transformer]] #Colab #Transformers #ComputerVision
+ [[https://openreview.net/pdf?id=tcjMxpMJc95][Understanding Knowledge Distillation]] #SemiSupervisedLearning #SelfSupervised #Distillation
+ [[https://thegradient.pub/why-skin-lesions-are-peanuts-and-brain-tumors-harder-nuts/][Why Skin Lesions are Peanuts and Brain Tumors Harder Nuts]] ~ T. Kooi #MedicalImaging #ScarceData
+ [[https://arxiv.org/pdf/2009.11060.pdf][Docs are ROCs: A simple off-the-shelf approach for estimating average human performance in diagnostic studies]] ~ L. Oakden-Rayner #Evaluation
+ [[https://arxiv.org/pdf/1906.02243.pdf][Energy and Policy Considerations for Deep Learning in NLP]] ~ E. Strubell #Energy
+ [[https://nips.cc/virtual/2020/public/invited_16166.html][You Can’t Escape Hyperparameters and Latent Variables: Machine Learning as a Software Engineering Enterprise ]] ~ C. Isbell #Neurips #Keynote #Bias #SoftwareEngineering
+ [[https://www.lamoncloa.gob.es/presidente/actividades/Documents/2020/021220-ENIA.pdf][Estrategia Nacional de Inteligencia Artificial]] #IA #Moncloa


** Noviembre 2020

+ [[https://walkwithfastai.com/tab.ae][Using AutoEncoders with Tabular Data (Intermediate)]] #FastAI #TabularData #AutoEncoders
+ [[https://arxiv.org/pdf/2010.05234.pdf][https://arxiv.org/pdf/2010.05234.pdf]] #GraphNeuralNetworks
+ [[https://arxiv.org/pdf/2010.09594.pdf][Multi-Modal Super Resolution for DenseMicroscopic Particle Size Estimation]] #SuperResolution #GAN #ObjectDetection
+ [[https://arxiv.org/pdf/2009.08576.pdf][Pruning Neural Networks at Initialization: Why are We Missing the Mark?]] #Prunning
+ [[https://www.pyimagesearch.com/2020/11/16/gans-with-keras-and-tensorflow/][GANs with Keras and TensorFlow]]  #Pyimagesearch #GANs 
+ [[https://www.pyimagesearch.com/2020/11/09/opencv-super-resolution-with-deep-learning/][OpenCV Super Resolution with Deep Learning]] #Pyimagesearch #SuperResolution #OpenCV
+ [[https://github.com/zszazi/Deep-learning-in-cloud][Deep-learning-in-cloud]] #Resources #DeepLearning #Cloud
+ [[https://nanonets.com/blog/key-value-pair-extraction-from-documents-using-ocr-and-deep-learning/][How to extract Key-Value pairs from Documents using deep learning]] #Forms #Athento
+ [[https://link.springer.com/article/10.1007%2Fs11548-020-02262-4][Unravelling the effect of data augmentation transformations in polyp segmentation]] #DataAugmentation #SemanticSegmentation
+ [[https://www.youtube.com/watch?v=-QH8fRhqFHM][The Narrated Transformer Language Model]] #NLP #Transformer
+ [[https://arxiv.org/pdf/2010.07922.pdf][Representation Learning via Invariant Causal Mechanisms]] #SelfSupervisedLearning
+ [[https://arxiv.org/abs/2010.09337][Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges]] #Interpretability
+ The ultimate guide to Encoder Decoder Models [[https://colab.research.google.com/drive/18ZBlS4tSqSeTzZAVFxfpNDb_SrZfAOMf?usp=sharing][1/4]] [[https://colab.research.google.com/drive/1XpKHijllH11nAEdPcQvkpYHCVnQikm9G?usp=sharing][2/4]] [[https://colab.research.google.com/drive/1HJhnWMFizEKKWEAb-k7QDBv4c03hXbCR?usp=sharing][3/4]] [[https://colab.research.google.com/drive/1BFgJbPSeAQE7Wz0hgqyaDJj_4wkUrXgt?usp=sharing][4/4]] #NLP Transformers
+ [[https://openreview.net/pdf?id=RLRXCV6DbEJ][Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images]] #VAE #GenerativeModels
+ [[https://openreview.net/pdf?id=qVyeW-grC2k][Long Range Arena : A Benchmark for Efficient Transformers ]] #Transformers #NLP
+ [[https://openreview.net/forum?id=YicbFdNTTy][An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale]] #Transformers #ImageClassification
+ [[https://arxiv.org/pdf/2009.11698.pdf][Principles and Practice of Explainable Machine Learning]] #Explanability
+ [[https://arxiv.org/pdf/1907.01297.pdf][Neural Network Verification for the Masses]] #TheoremProving #NeuralNetworks #Verification
+ [[https://github.com/aws-samples/amazon-sagemaker-endpoint-deployment-of-fastai-model-with-torchserve][Deploy FastAI Trained PyTorch Model in TorchServe]] #FastAI #Deployment
+ [[https://www.sciencedirect.com/science/article/pii/S0048969720362574#f0005][Deep learning approach for automatic microplastics counting and classification]] #Plastics #Segmentation #Classification

** Octubre 2020

+ [[https://arxiv.org/pdf/2010.00532.pdf][Persistent homology advances interpretable machine learning fornanoporous materials]] #TDA #PersistentHomology
+ [[https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123620069.pdf][Attentive Normalization]] #Normalization
+ [[https://www.lozeve.com/files/tdanetworks.pdf][Topological Data Analysis of Temporal Networks]] #TDA
+ [[http://jonathanstray.com/extracting-campaign-finance-data-from-gnarly-pdfs-using-deep-learning][Extracting campaign finance data from gnarly PDFs using deep learning]] ~ J. Stray #Forms #Athento
+ [[https://wandb.ai/stacey/deepform_v1/reports/DeepForm-Understand-Structured-Documents-at-Scale--VmlldzoyODQ3Njg][DeepForm: Understand Structured Documents at Scale]] #Forms #Athento
+ [[https://www.wandb.com/benchmarks][Weights and bias benchmarks]] #Datasets
+ [[https://wandb.ai/deepform/political-ad-extraction/benchmark][DeepForm: Extract Information from Documents]] #Dataset #Forms #Athento
+ [[http://jonathanstray.com/to-apply-ai-for-good-think-form-extraction][To apply AI for good, think form extraction]] ~ J. Stray #Forms #Athento
+ [[https://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-s897-machine-learning-for-healthcare-spring-2019/][Machine Learning for Healthcare]] #Healthcare #Course
+ [[https://arxiv.org/pdf/2003.00898.pdf][The importance of transparency and reproducibility in artificialintelligence research]] #Reproducibility
+ [[https://becominghuman.ai/using-variational-autoencoder-vae-to-generate-new-images-14328877e88d][Using Variational Autoencoder (VAE) to Generate New Images]] #VAE
+ [[https://arxiv.org/abs/2010.11430][Self-training and Pre-training are Complementary for Speech Recognition]] #SelfTraining #SpeechRecognition #PseudoLabeling
+ [[https://itsfoss.com/use-onedrive-linux-rclone/][https://itsfoss.com/use-onedrive-linux-rclone/]]
+ [[https://nanonets.com/blog/extract-structured-data-from-invoice/][How to extract structured data from invoices]] #Invoices #Athento
+ [[https://openaccess.thecvf.com/content_ICCV_2017/papers/Souly__Semi_Supervised_ICCV_2017_paper.pdf][Semi Supervised Semantic Segmentation Using Generative Adversarial Network]]  #SemanticSegmentation #SemiSupervisedLearning #GANs
+ [[https://arxiv.org/pdf/2010.09713v1.pdf][PseudoSeg: Designing Pseudo Labels for Semantic Segmentation]] #PseudoLabeling #SemanticSegmentation #SemiSupervisedLearning
+ [[https://arxiv.org/pdf/1912.10557.pdf][Algorithm Unrolling: Interpretable, Efficient DeepLearning for Signal and Image Processing]] #Interpretability
+ [[https://www.serch.dev/blog/2020/10/21/la-historia-que-cuentan-nuestros-tests.html][La historia que cuentan nuestros tests]] #TDD
+ [[https://www.pyimagesearch.com/2020/10/19/adversarial-images-and-attacks-with-keras-and-tensorflow/][Adversarial images and attacks with Keras and TensorFlow]] ~ A. Rosebrog #Pyimagesearch #AdversialAttacks
+ [[https://www.researchgate.net/publication/277775478_CRISP_Data_Mining_Methodology_Extension_for_Medical_Domain][CRISP Data Mining Methodology Extension for Medical Domain]]  #CRISPDM #Heidi #Medicine
+ [[https://www.researchgate.net/profile/Workneh_Ayele/publication/342572029_Adapting_CRISP-DM_for_Idea_Mining_A_Data_Mining_Process_for_Generating_Ideas_Using_a_Textual_Dataset/links/5efdc0baa6fdcc4ca444a952/Adapting-CRISP-DM-for-Idea-Mining-A-Data-Mining-Process-for-Generating-Ideas-Using-a-Textual-Dataset.pdf][Adapting CRISP-DM for Idea Mining]] #CRISPDM #Heidi
+ [[http://www.cs.unibo.it/~danilo.montesi/CBD/Beatriz/1107356429_CrispDM1.0.pdf][CRISP-DM 1.0]] #CRISPDM #Heidi
+ [[http://www.cs.unibo.it/~danilo.montesi/CBD/Beatriz/10.1.1.198.5133.pdf][CRISP-DM: Towards a Standard Process Model for Data Mining]] ~ R. Wirth #CRISPDM #Heidi
+ [[https://arxiv.org/abs/2009.08449]['Less Than One'-Shot Learning: Learning N Classes From M<N Samples]] ~ I. Sucholutsky #FewShotLearning
+ [[https://openreview.net/forum?id=xTJEN-ggl1b][LambdaNetworks: Modeling long-range Interactions without Attention]] #ComputerVision #ImageClassification
+ [[https://github.com/Machine-Learning-Tokyo/Interactive_Tools][Interactive Tools for ML, DL and Math]] #InteractiveTools
+ [[https://www.biorxiv.org/content/10.1101/2020.10.08.327718v1.full.pdf][Creating Clear and Informative Image-based Figures forScientific Publications]] ~ H. Hambor #Images
+ [[https://www.biorxiv.org/content/10.1101/2020.10.07.328005v1.full.pdf][1Deep-LUMEN Assay – Human lung epithelial spheroid classification from brightfield images using deep learning]] ~ L. Abdul #Detection #Spheroids #Tumours
+ [[https://github.com/vinthony/ghost-free-shadow-removal][Towards Ghost-free Shadow Removal]] ~ X. Cun #ShadowRemoval #GANs [[https://colab.research.google.com/drive/1cJ_dsBUXFaFtjoZB9gDYeahjmysnvnTq#scrollTo=qnoxUFU3zqpV][notebook]]
+ [[https://openaccess.thecvf.com/content_ICCV_2019/papers/Hu_Mask-ShadowGAN_Learning_to_Remove_Shadows_From_Unpaired_Data_ICCV_2019_paper.pdf][Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data]] ~ X. Hu #ShadowRemoval #CycleGAN
+ [[https://arxiv.org/abs/2009.10521][A survey on Kornia: an Open Source Differentiable Computer Vision Library for PyTorch]] ~ E. Riba #ComputerVision #DeepLearning
+ [[https://arxiv.org/pdf/1812.03443.pdf][FBNet: Hardware-Aware Efficient ConvNet Designvia Differentiable Neural Architecture Search]] ~ B. Wu #FBNet #Mobile
+ [[https://arxiv.org/pdf/2003.12040.pdf][Pseudo-Labeling for Small Lesion Detection onDiabetic Retinopathy Images]] ~ Q. Chen #DiabeticRetinopathy #PseudoLabeling #ObjectDetection #SemiSupervisedLearning
+ [[https://distill.pub/2020/communicating-with-interactive-articles/][Communicating with Interactive Articles]] ~ F. Hohman #Distill
+ [[http://anna.harutyunyan.net/wp-content/uploads/2020/09/What_is_an_agent.pdf][What is an agent?]] ~ A. Harutyunyan #ArtificialIntelligence
+ [[https://news.cision.com/fi/city-of-helsinki/r/helsinki-and-amsterdam-first-cities-in-the-world-to-launch-open-ai-register,c3204076][Helsinki and Amsterdam first cities in the world to launch open AI register]] #Cities #ArtificialIntelligence
+ [[https://github.com/genforce/genforce][GenForce Lib for Generative Modeling]] #GANs
+ [[https://www.kaggle.com/tanlikesmath/upit-a-package-for-unpaired-img2img-translation/][UPIT -a package for unpaired img2img translation]] #Image2Image #CycleGAN

** Septiembre 2020

+ [[https://arxiv.org/pdf/1807.07356.pdf][Aleatoric uncertainty estimation with test-time augmentation for medical imagesegmentation with convolutional neural networks]] ~ G. Wang #TTA #SemanticSegmentation
+ [[https://www.nature.com/articles/s41598-020-61808-3][Test-time augmentation for deep learning-based cell segmentation on microscopy images]] ~ N. Moshk #TestTimeAugmentation #SemanticSegmentation 
+ [[https://lilianweng.github.io/lil-log/2018/11/30/meta-learning.html][Meta-Learning: Learning to Learn Fast]] ~ L. Weng #MetaLearning
+ [[https://arxiv.org/pdf/1906.01916.pdf][Semi-supervised semantic segmentationneeds strong, varied perturbations]] ~ G. French #SemiSupervisedLearning #SemanticSegmentation
+ [[https://arxiv.org/pdf/1912.02781.pdf][AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty]] ~ D. Hendrycks #DataAugmentation
+ [[https://arxiv.org/abs/1905.04899][CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features]] ~ S. Yun #DataAugmentation
+ [[https://arxiv.org/pdf/2009.06489.pdf][The Hardware Lottery]] ~ S. Hooker #Essay #Hardware #DeepLearning
+ [[https://www.pcmag.com/news/the-next-step-toward-improving-ai][The Next Step Toward Improving AI]] ~ B. Dickson #Interpretability
+ [[https://www.nature.com/articles/s41586-020-2649-2.pdf][Array programming with NumPy]] ~ C. Harris #Numpy
+ [[https://arxiv.org/pdf/2008.08579.pdf][Slide-free MUSE Microscopy to H&E Histology Modality Conversionvia Unpaired Image-to-Image Translation GAN Models]] ~ T. Abraham #GANs #StyleTransfer 
+ [[https://www.mdpi.com/2072-4292/12/16/2532/htm][Fully Convolutional Neural Network for Rapid Flood Segmentation in Synthetic Aperture Radar Imagery ]] ~ E. Nemni #Fastai #Lidar #Copernicus
+ [[https://www.sciencedirect.com/science/article/pii/S2001037020303561][A bird’s-eye view of deep learning in bioimage analysis]] ~ E. Meijering #DeepLearning #Bioimaging #Survey #AutoML
+ [[https://arxiv.org/abs/2001.00018][Connecting optical morphology, environment, and HI mass fraction for low-redshift galaxies using deep learning]] ~ J. Wu #Galaxies #FastAI
+ [[https://docs.google.com/spreadsheets/d/1wZhPLMCHKJvwOkP4juclhjFgqIY8fQFMemwKL2c64vk/edit#gid=0][Data is plural]] ~ J. Singer-Vine #Datasets
+ [[https://arxiv.org/pdf/2009.00236v1.pdf][A Survey of Deep Active Learning]] ~ P. Ren #ActiveLearning
+ [[https://www.quantamagazine.org/how-close-are-computers-to-automating-mathematical-reasoning-20200827/][How Close Are Computers to Automating Mathematical Reasoning?]] ~ S. Ornes #ITP
+ [[https://labs.loc.gov/work/reports/][Library reports]] #Libraries
+ [[https://yassouali.github.io/ml-blog/cvpr2020/][CVPR 2020: A Snapshot]] ~ Y. Ouali #Summarcy #CVPR
+ [[https://yassouali.github.io/ml-blog/eccv2020/][ECCV 2020: Some Highlights]] ~ Y. Ouali #Summarcy #ECCV
+ [[https://samiraabnar.github.io/articles/2020-05/vizualization][Visualizing Model Comparison]] ~ S. Abnar #ModelComparison
+ [[https://samiraabnar.github.io/articles/2020-05/recurrence][On the Merits of Recurrent Inductive Bias]] ~ S. Abnar #NLP #Bias
+ [[https://timdettmers.com/2020/09/07/which-gpu-for-deep-learning/][Which GPU(s) to Get for Deep Learning: My Experience and Advice for Using GPUs in Deep Learning]] ~ T. Dettmers #GPUs
+ [[https://github.com/davanstrien/fastai4GLAMS][fastai4GLAMS study group]] ~ davastrien #Datasets #Museums #ObjectDetection #Classification #Athento
+ [[http://icaart.org/ARTIDIGH.aspx][Artificial Intelligence and Digital Heritage: Challenges and Opportunities - ARTIDIGH 2021 ]] ~ Conference #ArtificialIntelligence #Museums
+ [[https://arxiv.org/pdf/2009.01564.pdf][Can AutoML outperform humans? An evaluation on popular OpenML datasets using AutoML Benchmark]] ~ M. Hanussek #AutoML
+ [[https://arxiv.org/pdf/2006.05278.pdf][An Overview of Deep Semi-Supervised Learning]] ~ Y. Ouali #SemiSupervisedLearning #Review
+ [[https://arxiv.org/pdf/2003.09005.pdf][Semi-Supervised Semantic Segmentation with Cross-Consistency Training]]  ~ Y. Ouali #SemanticSegmentation #SemiSupervisedLearning
+ [[https://github.com/yassouali/awesome-semi-supervised-learning][Awesome Semi-Supervised Learning]] ~ Y. Ouali #SemiSupervisedLearning #CuratedList
+ [[https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0029740][Color-to-Grayscale: Does the Method Matter in Image Recognition?]] ~ C. Kanan #ImageUnderstanding
+ [[https://arxiv.org/pdf/2001.06001.pdf][Curriculum Labeling: Self-paced Pseudo-Labeling forSemi-Supervised Learning]] ~ P. Cascante-Bonilla #CurriculumLearning #SemiSupervisedLearning
+ [[https://sites.google.com/view/di2019/home][https://sites.google.com/view/di2019/home]] #Athento #DocumentAnalysis #Workshop
+ [[https://arxiv.org/pdf/1912.13318.pdf][LayoutLM: Pre-training of Text and Layout for Document Image Understanding]] ~ Y. Xu #Transformers #DocumentAnalysis #FormUnderstanding #FUNSD [[https://github.com/microsoft/unilm/tree/master/layoutlm][Repository]]
+ [[https://icdar2021.org/competitions/][COMPETITION ON SCIENTIFIC LITERATURE PARSING]] ~ ICDAR #Athento #Competitions
+ [[https://arxiv.org/abs/2006.01038][DocBank: A Benchmark Dataset for Document Layout Analysis]] ~ M. Li #DocumentAnalysis #Dataset
+ [[https://arxiv.org/pdf/2009.00104.pdf][A Framework For Contrastive Self-SupervisedLearning And Designing A New Approach]] ~ W. Falcon #SelfSupervisedLearning #ContrastiveLearning

** Agosto 2020

+ [[https://huggingface.co/blog/reformer][The Reformer - Pushing the limits of language modeling]] ~ P. von Platen #NLP #Reformer #HuggingFace
+ [[https://papers.eccv2020.eu/paper/2209/][MimicDet: Bridging the Gap BetweenOne-Stage and Two-Stage Object Detection]] ~ X. Lu #ObjectDetection #ECCV
+ [[https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123480154.pdf][ForkGAN: Seeing into the Rainy Night]] ~ Z. Zheng #DomainTranslation #Detection #ECCV
+ [[https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123740579.pdf][Improving Object Detection withSelectiveSelf-Supervised Self-Training]] ~ Y. Li #SelfSupervisedLearning #ObjectDetection #ECCV
+ [[https://docs.google.com/document/d/11D3kHElzS2HQxTwPqcaTnU5HCJ8WGE5brTXI4KLf4dM][Syllabus for Eric's PhD students]] ~ E. Gilbert #Advice #PhDStudents
+ [[https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123730069.pdf][Table Structure Recognition using Top-Downand Bottom-Up Cues]] ~ S. Raja #Athento #TableStructure
+ [[https://www.cs.mcgill.ca/~wlh/grl_book/files/GRL_Book.pdf][Graph Representation Learning]] ~ W. Hamilton #GraphRepresentationLearning #Book
+ [[https://amaarora.github.io/2020/08/23/siimisic.html][SIIM-ISIC Melanoma Classification - my journey to a top 5% solution and first silver medal on Kaggle]] ~ A. Arora #ImageClassification #Tips
+ [[https://arxiv.org/pdf/2004.12629.pdf][CascadeTabNet: An approach for end to end table detection and structurerecognition from image-based documents]] ~ D. Prasad #TableSegmentation #TableDetection #Athento [[https://github.com/DevashishPrasad/CascadeTabNet][Repository]]
+ [[https://dbolya.github.io/tide/paper.pdf][TIDE: A General Toolbox for Identifying Object Detection Errors]] ~ D. Bolya #Evaluation #Object Detection
+ [[https://arxiv.org/pdf/2007.01293v1.pdf][Not All Unlabeled Data are Equal:Learning to Weight Data in Semi-supervised Learning]] ~ Z. Ren #SemiSupervisedLearning
+ [[https://blog.openmined.org/private-machine-learning-explained/][Privacy-Preserving Data Science, Explained]] ~ E. Bluenke #Privacy
+ [[http://ethics.fast.ai/][Practical data ethics]] ~ R. Thomas #Ethics #Data
+ [[https://www.youtube.com/watch?feature=youtu.be&v=ZAW9EyNo2fw&app=desktop][Reconciling modern machine learning and the bias-variance trade-off (video)]] ~ Y. Kilcher  #BiasVarianceTradeoff
+ [[https://www.vanderschaar-lab.com/automl-powering-the-new-human-machine-learning-ecosystem/][AutoML: powering the new human-machine learning ecosystem]] ~ Mihaela van der Schaar #AutoML
+ [[https://towardsdatascience.com/github-is-the-best-automl-you-will-ever-need-5331f671f105][GitHub is the best AutoML you will ever need]] ~ M. Ali #GitHub #MLOps
+ [[https://www.kaggle.com/amyjang/neural-style-transfer-for-augmenting-medical-data?linkId=96670625][Neural Style Transfer for Augmenting Medical Data]] ~ A. Yang #StyleTransfer #MedicalImaging
+ [[https://amaarora.github.io/2020/08/13/efficientnet.html][EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks]] ~ A. Arora #EfficientNet #ImageClassification
+ [[https://medium.com/@nainaakash012/unsupervised-learning-of-visual-features-by-contrasting-cluster-assignments-fbedc8b9c3db][Unsupervised Learning of Visual Features by Contrasting Cluster Assignments]] ~ A. Nain #SelfSupervisedLearning
+ [[https://analyticsindiamag.com/how-do-data-scientists-create-high-quality-training-datasets-for-computer-vision/][How Do Data Scientists Create High-Quality Training DataSets For Computer Vision ]] ~ V. Chawla #Datasets #ComputerVision
+ [[https://elifesciences.org/articles/55133][Imaging methods are vastly underreported in biomedical research]] ~ G. Marques #Imaging #Reproducibility
+ [[https://towardsdatascience.com/12-papers-you-should-read-to-understand-object-detection-in-the-deep-learning-era-3390d4a28891][12 Papers You Should Read to Understand Object Detection in the Deep Learning Era]] ~ E. Yanjia Li #ObjectDetection
+ [[https://jalammar.github.io/how-gpt3-works-visualizations-animations/][How GPT3 Works - Visualizations and Animations]] ~ J. Alamar #GPT3 #NLP
+ [[https://towardsdatascience.com/pp-yolo-surpasses-yolov4-object-detection-advances-1efc2692aa62][PP-YOLO Surpasses YOLOv4 — Object Detection Advances]] ~ J. Solawetz #PPYolo #ObjectDetection #PaddlePaddle
+ [[https://github.com/NirantK/awesome-project-ideas#vision][Awesome Deep Learning Project Ideas]] ~ NirantK #DeepLearning #Projects
+ MLOps Tutorial [[https://www.youtube.com/watch?v=9BgIDqAzfuA][Video 1]] [[https://www.youtube.com/watch?feature=youtu.be&v=kZKAuShWF0s&app=desktop][Video 2]] [[https://www.youtube.com/watch?v=xPncjKH6SPk&feature=youtu.be][Video 3]] ~ E. Obrien #MLOps
+ [[https://www.qblocks.cloud/creators/computer-vision-google-colab-notebooks][Top Computer Vision Google Colab Notebooks]] #Colab #ComputerVision #Resources
+ [[https://ruder.io/nlp-beyond-english/][Why You Should Do NLP Beyond English]] ~ S. Ruder #NLP

** Julio 2020

+ [[https://arxiv.org/pdf/1611.07004.pdf][Image-to-Image Translation with Conditional Adversarial Networks]] ~ P. Isola #Image2Image #GAN
+ [[https://medium.com/@jonathan_hui/gan-wasserstein-gan-wgan-gp-6a1a2aa1b490][GAN — Wasserstein GAN & WGAN-GP]] ~ J. Hui #GANs
+ [[https://arxiv.org/abs/1711.06897][Single-Shot Refinement Neural Network for Object Detection]] ~ S. Zhang #ObjectDetection
+ [[https://arxiv.org/abs/1706.05587][Rethinking Atrous Convolution for Semantic Image Segmentation]] ~ L. Chen #SemanticSegmentation #AtrousConvolution
+ [[https://arxiv.org/pdf/1810.03993.pdf][Model Cards for Model Reporting]] ~ M. Mitchel #Provenance [[https://modelcards.withgoogle.com][Model cards webpage]]
+ [[https://cloud.google.com/blog/products/ai-machine-learning/google-breaks-ai-performance-records-in-mlperf-with-worlds-fastest-training-supercomputer][Google breaks AI performance records in MLPerf with world's fastest training supercomputer]] ~ N. Kumar #SuperComputing #TPUs
+ [[https://arxiv.org/pdf/2007.08558.pdf][On Robustness and Transferability ofConvolutional Neural Networks]] ~ J. Djolonga #Robustness #TransferLearning
+ [[http://cdn.iiit.ac.in/cdn/cvit.iiit.ac.in/images/ConferencePapers/2019/PID6011471.pdf][Graphical Object Detection in Document Images]] #Dataset #ImageAnalysis
+ [[https://sci-hub.tw/10.1109/CVPR.2019.00489][What does it mean to learn in deep networks? And, how does one detectadversarial attacks?]] ~ C. Corneanu #AlgebraicTopology #DeepLearning
+ [[https://adversarial-ml-tutorial.org/][Adversarial Robustness - Theory and Practice]] ~ Z.  Kolter #AdversarialExamples
+ [[https://arxiv.org/pdf/2003.07631.pdf][Toward Interpretable Machine Learning:Transparent Deep Neural Networks and Beyond]] ~ W: Samek #Interpretability
+ [[https://arxiv.org/pdf/2007.07365.pdf][Towards a Theoretical Understanding of the Robustness ofVariational Autoencoders]] ~ A. Camuto #AdversarialAttacks #VAEs
+ [[https://arxiv.org/pdf/2007.06776.pdf][Verification of ML Systems via Reparameterization]] ~ J.B. Tristan #TheoremProving #Verification
+ [[https://arxiv.org/pdf/2007.08792.pdf][Uncertainty Quantification and Deep Ensembles]] ~ R. Rahaman #Ensembles
+ [[https://yasoob.me/posts/understanding-and-writing-jpeg-decoder-in-python/][Understanding and Decoding a JPEG Image using Python]] ~ Y. Khalid #JPG #Algorithms
+ [[https://app.wandb.ai/authors/tfaugmentation/reports/Modern-Data-Augmentation-Techniques-for-Computer-Vision--VmlldzoxNzU3NTU][Modern Data Augmentation Techniques for Computer Vision]] ~ A. Thakur #DataAugmentation
+ [[https://arxiv.org/pdf/1706.02515.pdf][Self-Normalizing Neural Networks]] ~ G. Klambauer #StructuredData
+ [[https://arxiv.org/pdf/1910.03771.pdf][Transformers: State-of-the-Art Natural Language Processing]] ~ Huggingface #NLP #Transformers
+ [[http://jalammar.github.io/illustrated-gpt2/][The Illustrated GPT-2 (Visualizing Transformer Language Models)]] ~ J. Alammar #NLP #GPT2
+ [[https://medium.com/@pierre_guillou/faster-than-training-from-scratch-fine-tuning-the-english-gpt-2-in-any-language-with-hugging-f2ec05c98787][Faster than training from scratch — Fine-tuning the English GPT-2 in any language with Hugging Face and fastai v2 (practical case with Portuguese)]] ~ P. Guillou #NLP #Transformers #HuggingFace #FastAI
+ [[https://arxiv.org/pdf/1804.08328.pdf][Taskonomy: Disentangling Task Transfer Learning]] ~ A. Zamir #TransferLearning
+ [[https://arxiv.org/pdf/2007.10928.pdf][What is important about the No Free Lunch theorems?]] ~ D. Wolpert #NoFreeLunchTheorem
+ [[https://francescopochetti.com/tabular-deep-leaning-tabnet-deep-dive/][Tabular Deep Leaning: TabNet deep dive]] ~ F. Pochetti #TabNet
+ [[https://arxiv.org/pdf/2006.02334.pdf][DetectoRS: Detecting Objects with Recursive Feature Pyramidand Switchable Atrous Convolution]] ~ S. Qiao #ObjectDetection
+ [[https://link.springer.com/content/pdf/10.1007%2F978-3-030-53518-6_1.pdf][A Promising Path Towards Autoformalization and General ArtificialIntelligence]] ~ C. Szegedy #Formalization #ITP #AGI
+ [[https://arxiv.org/pdf/2007.02171.pdf][Neuro-Symbolic Generative Art: A Preliminary Study]] ~ G. Aggarwal #Art #GenerativeLearning
+ [[https://arxiv.org/pdf/2007.07628v1.pdf][Visualizing Transfer Learning]] ~ R. Szabó #TransferLearning #Visualization
+ [[https://keras.io/examples/vision/image_classification_efficientnet_fine_tuning/][Image classification via fine-tuning with EfficientNet]] ~ Y. Fu #Keras #EfficientNet #FineTuning
+ [[https://papers.nips.cc/paper/8717-when-does-label-smoothing-help.pdf][When Does Label Smoothing Help?]] ~ R. Muller #LabelSmoothing #ImageClassification
+ [[http://vladlen.info/papers/self-attention.pdf][Exploring Self-attention for Image Recognition]] ~ H. Zao #Attention #ImageClassification
+ [[https://openai.com/blog/openai-api/][OpenAI API]] ~ OpenAI #NLP #GPT3
+ [[https://sites.google.com/view/chiawen-kuo/home/featmatch][FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning]] ~ C-W. Keo #SemiSupervisedLearning #ImageAugmentation
+ [[https://ruder.io/optimizing-gradient-descent/][An overview of gradient descent optimization algorithms]] ~ S. Ruder #Training #Optimization
+ [[https://graphics.pixar.com/library/SuperResolution/paper.pdf][Deep Learned Super Resolution for Feature Film Production]] ~ V. Vavilana #SuperResolution #Pixar
+ [[https://docs.google.com/presentation/d/1mvmJ1PnCe7lWGmSoL80CjLe7N2QpEwkU8x7l62BawME/edit#slide=id.p1][Machine Learning Production Pipeline]] ~ C. Huyen #Pipeline #Production
+ [[https://medium.com/usf-msds/creating-a-web-application-powered-by-a-fastai-model-d5ee560d5207][Creating a web application powered by a fastai model]] ~ A. NS #FastAI #WebAPP #Flask
+ [[https://www.aclweb.org/anthology/2020.acl-main.204.pdf][DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference]] ~ J. Xin #NLP #Bert
+ [[https://course.fullstackdeeplearning.com][Full stack deep learning]] #DeepLearning #Course #EndToEnd
+ [[https://github.com/tensorflow/cloud][TensorFlow Cloud]] #Tensorflow #Cloud
+ [[https://www.youtube.com/watch?v=C_lBYKV_pJo&feature=youtu.be][Quantum Machine Learning]] ~ M. Schuld #MachineLearning #QuantumComputing
+ [[https://medium.com/@ndharap/data-pipelines-in-fastai-v1-4c927d7757d2][Data Pipelines in Fastai (data blocks API v1)]] ~ N. Dharap #FastAI
+ [[https://blog.tensorflow.org/2020/07/tensorflow-2-meets-object-detection-api.html][TensorFlow 2 meets the Object Detection API]] ~ V. Rathod #ObjectDetection #Tensorflow
+ [[https://machinelearningmastery.com/model-based-outlier-detection-and-removal-in-python/][4 Automatic Outlier Detection Algorithms in Python]] ~ J. Brownlee #OutlierDetection
+ [[https://21stcenturychallenges.org/challenges/][21st Century Challenges]] #Challenges
+ [[https://amitness.com/2020/07/semi-supervised-learning/][Semi-Supervised Learning in Computer Vision]] ~ A. Chaudhary #SemiSupervisedLearning #Review
+ [[https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-020-03635-x][Keras R-CNN: library for cell detection inbiological images using deep neuralnetworks]] ~ J. Hung #DeepLearning #ObjectDetetion [[https://github.com/broadinstitute/keras-rcnn][#KerasRCNN]]
+ [[https://danilorezende.com/wp-content/uploads/2020/07/ICML-2020-Tutorial-Slides.pdf][Representation learning without labels]] ~ I. Higgins #RepresentationLearning
+ [[https://storage.googleapis.com/deepmind-media/UCLxDeepMind_2020/L12%20-%20UCLxDeepMind%20DL2020.pdf][Responsible Innovation & Artificial Intelligence]] ~ C. Qin #AdversialTraining #Ethics
+ [[https://www.youtube.com/watch?v=x6T1zMSE4Ts&feature=youtu.be][NVAE: A Deep Hierarchical Variational Autoencoder (Paper Explained)]] ~ Y. Kilcher #AutoEncoders
+ [[https://www.sciencedirect.com/science/article/pii/S1361841519301100?via%3Dihub][REFUGE Challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs]] ~ J. Orlando #Challenge #ImageClassification #ImageSegmentation
+ [[https://arxiv.org/pdf/1812.01187.pdf][Bag of Tricks for Image Classification with Convolutional Neural Networks]] ~ T. He #Tricks #ImageClassification
+ [[https://arxiv.org/pdf/1803.05316.pdf][Seven Sketches in Compositionality:An Invitation to Applied Category Theory]] ~ B. Frog #CategoryTheory
+ [[https://www.youtube.com/watch?v=hAooAOFRsYc&feature=youtu.be][Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention (Paper Explained)]] ~ Y. Kilcher #Attention #RNN
+ [[https://arxiv.org/pdf/1908.07442.pdf][TabNet: Attentive Interpretable Tabular Learning]] ~ S. Arik #TabularData #SelfSupervisedLearning #Attention
+ [[https://distill.pub/2020/bayesian-optimization/][Exploring Bayesian Optimization]] ~ A. Agnihotri #Tuning
+ [[https://blog.floydhub.com/introduction-to-adversarial-machine-learning/][Introduction to Adversarial Machine Learning]] ~ A. Chakraborty #AdversarialExamples
+ [[https://roberttlange.github.io/posts/2020/06/lottery-ticket-hypothesis/][The Lottery Ticket Hypothesis: A Survey]] ~ R. Lange #LotteryTicket
+ [[https://link.springer.com/content/pdf/10.1007%2F978-3-030-51054-1_6.pdf][Deep Generation of Coq Lemma Names Using Elaborated Terms]] ~ P. Nie #NLP #Coq
+ [[https://www.youtube.com/watch?v=qFRfnIRMNlk][SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization (Paper Explained)]] ~ Y. Kilcher #CNNs #Classification #ObjectDetection
+ [[https://openaccess.thecvf.com/content_WACV_2020/papers/Vitoria_ChromaGAN_Adversarial_Picture_Colorization_with_Semantic_Class_Distribution_WACV_2020_paper.pdf][ChromaGAN: Adversarial Picture Colorization with Semantic Class Distribution]] ~ P. Vitoria #Colorization #GANs
+ [[https://arxiv.org/pdf/1912.05027.pdf][SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization]] ~ X. Du #NeuralArchitectureSearch
+ [[https://github.com/Adi-iitd/AI-Art][AI Art]] #DeepDream #Pix2Pix #StyleTransfer #CycleGAN
+ [[https://arxiv.org/pdf/2007.00224.pdf][Debiased Contrastive Learning]] ~ C-Y. Chuang #SelfSupervisedLearning #ContrastiveLearning
+ [[https://arxiv.org/pdf/2006.10029.pdf][Big Self-Supervised Models areStrong Semi-Supervised Learners]] ~ T. Chen #SelfSupervisedLearning #SemiSupervisedLearning
+ [[https://t.co/pE4NG6s8lv?amp=1][Opening Up the Black Box: Model Understanding with Captum and PyTorch]] ~ N. Kokhlikyan #Interpretability #Pytorch 
+ [[https://openaccess.thecvf.com/content_CVPR_2020/papers/Dundar_Panoptic-Based_Image_Synthesis_CVPR_2020_paper.pdf][Panoptic-based Image Synthesis]] ~ A. Dundar #ImageSynthesis
+ [[https://www.youtube.com/watch?v=q6Kyvy1zLwQ&feature=youtu.be][BERTology Meets Biology: Interpreting Attention in Protein Language Models (Video Explained)]] ~ Y. Kilcher #Bert #Biologoy #Proteins
+ The Reformer [[https://colab.research.google.com/drive/15oP52_7W5dRcAnbgX3tYADsu4R3cjMIf?usp=sharing][Notebook 1]] [[https://colab.research.google.com/drive/1xKK32Yhda-iYgtoA3eCrnCVuy_lraQR9?usp=sharing][Notebook 2]] [[https://colab.research.google.com/drive/1BLffcRt9LXmM7nKU2UXhtm0PqAG0UE7J?usp=sharing][Notebook 3]] [[https://colab.research.google.com/drive/1MYxvC4RbKeDzY2lFfesN-CvPLKLk00CQ?usp=sharing][Notebook 4]] #NLP
+ [[https://www.youtube.com/watch?v=JpkzK58lkmA][Designing Practical NLP Solutions]] ~ I. Montani #NLP
+ [[https://academic.oup.com/jamia/article/25/10/1419/5035024][Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review]] ~ C. Xiao #Review #HealthRecords
+ [[https://arxiv.org/abs/1911.01547][The Measure of Intelligence]] ~ F. Chollet #Intelligence #ArtificialIntelligence
+ [[https://ai.facebook.com/blog/a-new-dense-sliding-window-technique-for-instance-segmentation/][A new dense, sliding-window technique for instance segmentation]] ~ Facebook #InstanceSegmentation
+ [[https://www.robots.ox.ac.uk/~vgg/publications/2012/Arandjelovic12/arandjelovic12.pdf][Three things everyone should know to improve object retrieval]] ~ R. Arandjelovic #ObjectRetrieval #DatabaseSearch
+ [[https://www.nature.com/articles/s41591-020-0942-0.pdf][Human–computer collaboration for skin cancer recognition]] ~ P. Tschandl #MedicalImaging
+ [[http://openaccess.thecvf.com/content_CVPRW_2020/papers/w45/Lee_SmoothMix_A_Simple_Yet_Effective_Data_Augmentation_to_Train_Robust_CVPRW_2020_paper.pdf][SmoothMix: a Simple Yet Effective Data Augmentation to Train RobustClassifiers]] ~ J. H. Lee #DataAugmentation
+ [[http://mlss.tuebingen.mpg.de/2020/schedule.html][The Machine Learning Summer School]] #MachineLearning #Course
+ [[http://openaccess.thecvf.com/content_CVPR_2020/papers/Corneanu_Computing_the_Testing_Error_Without_a_Testing_Set_CVPR_2020_paper.pdf][Computing the Testing Error without a Testing Set]] ~ C. Corneanu #PersistentHomology #MachineLearning
+ [[https://ai.googleblog.com/2020/04/advancing-self-supervised-and-semi.html][Advancing Self-Supervised and Semi-Supervised Learning with SimCLR ]] ~ T. Chen #SelfSupervisedLearning #SemiSupervisedLearning
+ [[https://towardsdatascience.com/distributed-learning-on-image-classification-of-beans-in-tensorflow-5a85e6c3eb71][Distributed Learning on Image Classification of Beans in TensorFlow]] ~ A. Gupta #DistributedLearning #Tensorflow

** Junio 2020

#+html: <p align="center"><img src="wordClouds/junio2020.png" /></p>
+ [[https://www.youtube.com/watch?v=DYBmD88vpiA][Object-Centric Learning with Slot Attention (Paper Explained)]] ~ Y. Kilcher #Attention 
+ ̣[[https://www.youtube.com/watch?v=Hdo81GtLC_4][Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures (Paper Explained)]] ~ Y. Kilcher #BackPropagationAlternative #Training
+ [[https://www.researchgate.net/profile/Jorge_Calvo-Zaragoza/publication/335333672_Handwritten_Music_Recognition_for_Mensural_Notation_with_Convolutional_Recurrent_Neural_Networks/links/5d650fac299bf1f70b101c7a/Handwritten-Music-Recognition-for-Mensural-Notation-with-Convolutional-Recurrent-Neural-Networks.pdf][Handwritten Music Recognition for Mensural Notation with Convolutional RecurrentNeural Networks]] ~ J. Calvo-Zaragoza #OMR
+ [[https://ieeexplore.ieee.org/document/8999506][Using Cell Phone Pictures of Sheet Music To Retrieve MIDI Passages]] ~ T. Tsai #OMR
+ [[https://github.com/apacha/OMR-Datasets][Optical Music Recognition Datasets]] #OMR #Datasets
+ [[https://arxiv.org/abs/1912.03538][Context R-CNN: Long Term Temporal Context for Per-Camera Object Detection]] ~ S. Beery #ObjectDetection #Attention
+ [[http://carabela.prhlt.upv.es/en/][Carabela]] ~ E. Vidal #OCR #OldDocuments #Athento
+ [[https://arxiv.org/pdf/2006.09965.pdf][High-Fidelity Generative Image Compression]] ~ F. Mentzer #GANs #ImageCompression
+ [[http://openaccess.thecvf.com/content_CVPRW_2020/papers/w57/Battiato_Detection_and_Classification_of_Pollen_Grain_Microscope_Images_CVPRW_2020_paper.pdf][Detection and Classification of Pollen Grain Microscope Images]] ~ S. Battiano #ImageClassification #Bioimage
+ [[http://openaccess.thecvf.com/content_CVPR_2020/papers/Tang_A_Semi-Supervised_Assessor_of_Neural_Architectures_CVPR_2020_paper.pdf][A Semi-Supervised Assessor of Neural Architectures]] ~ Y. Tang #NeuralArchitectureSearch
+ [[http://openaccess.thecvf.com/content_CVPR_2020/papers/Chen_Adversarial_Robustness_From_Self-Supervised_Pre-Training_to_Fine-Tuning_CVPR_2020_paper.pdf][Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning]] ~ T. Chen #AdversialRobustness #SelfSupervisedLearning #TransferLearning
+ [[https://arxiv.org/pdf/2006.07159.pdf][Are we done with ImageNet?]] ~ L. Beyer #ImageNet #Evaluation #Benchmark
+ [[http://openaccess.thecvf.com/content_CVPR_2019/papers/Feng_Self-Supervised_Representation_Learning_by_Rotation_Feature_Decoupling_CVPR_2019_paper.pdf][Self-Supervised Representation Learning by Rotation Feature Decoupling]] ~ Z. Feng #SelfSupervisedLearning #AdversialAttacks
+ [[https://ranahanocka.github.io/point2mesh/][Point2Mesh A Self-Prior for Deformable Meshes]] ~ R. Hanocka #Mesh #Topology
+ [[https://www.frontiersin.org/articles/10.3389/fpls.2017.01190/full][Deep Plant Phenomics: A Deep Learning Platform for Complex Plant Phenotyping Tasks]] ~ J. Ubbens #DeepLearning #Plants
+ [[http://openaccess.thecvf.com/content_CVPRW_2020/papers/w5/Khan_A_Novel_Technique_Combining_Image_Processing_Plant_Development_Properties_and_CVPRW_2020_paper.pdf][A Novel Technique Combining Image Processing, Plant Development Properties,and the Hungarian Algorithm, to Improve Leaf Detection in Maize]] ~ N. A. Kham #Plants #Agriculture #Skeleton
+ [[https://dennybritz.com/blog/ai-replication-incentives/][AI Research, Replicability and Incentives]] ~ D. Britz #Replicability #Reproducibility 
+ [[https://arxiv.org/abs/1808.01244][CornerNet: Detecting Objects as Paired Keypoints]] ~ H. Law #ObjectDetection
+ [[https://arxiv.org/abs/2006.07733][Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning]] ~ J-B. Grill #SelfSupervisedLearning
+ [[https://arxiv.org/pdf/2006.06882.pdf][Rethinking Pre-training and Self-training]] ~ B. Zoph #TransferLearning #SemiSupervisedLearning
+ [[http://openaccess.thecvf.com/content_CVPR_2020/papers/Peng_Deep_Snake_for_Real-Time_Instance_Segmentation_CVPR_2020_paper.pdf][Deep Snake for Real-Time Instance Segmentation]] ~ S. Peng #InstanceSegmentation #Contours #Snake
+ [[http://mlops-github.com/][Machine Learning Ops]] #MLOps
+ [[https://interpretablevision.github.io/][CVPR 2020 Tutorial on Interpretable Machine Learning for Computer Vision]] #Interpretability #Tutorial
+ [[https://www.mdpi.com/2078-2489/11/3/137/htm][A Responsible Machine Learning Workflow with Focus on Interpretable Models, Post-hoc Explanation, and Discrimination Testing]] ~ N. Gill #Interpretable #Fairness
+ [[https://www.pyimagesearch.com/2020/06/15/opencv-fast-fourier-transform-fft-for-blur-detection-in-images-and-video-streams/][OpenCV Fast Fourier Transform (FFT) for blur detection in images and video streams]] ~ A. Rosebrock #Pyimagesearch #BlurDetection #FourierTransform
+ [[https://public.roboflow.ai/object-detection/][Object Detection Datasets]] ~ Roboflow #ObjectDetection #Datasets
+ [[https://keras.io/examples/structured_data/structured_data_classification_from_scratch/][Structured data classification from scratch]] ~ F. Chollet #Keras #StrucuturedData
+ [[https://arxiv.org/pdf/2006.06666.pdf][VirTex: Learning Visual Representationsfrom Textual Annotations]] ~ K. Desai #Pretraining #SelfSupervisedLearning #TransferLearning 
+ [[https://nostalgebraist.tumblr.com/post/185326092369/the-transformer-explained][The transformer explained]] #Transfomers #NLP
+ [[http://openaccess.thecvf.com/content_CVPR_2020/papers/Yuan_Ensemble_Generative_Cleaning_With_Feedback_Loops_for_Defending_Adversarial_Attacks_CVPR_2020_paper.pdf][Ensemble Generative Cleaning with Feedback Loops for Defending AdversarialAttacks]] ~ J. Yuan #Ensembles #AdversarialAttacks
+ [[http://openaccess.thecvf.com/content_CVPR_2020/papers/Naseer_A_Self-supervised_Approach_for_Adversarial_Robustness_CVPR_2020_paper.pdf][A Self-supervised Approach for Adversarial Robustness]] ~ M. Nasser #SelfSupervisedLearning #AdversarialAttacks #Detection #Segmentation #Classification
+ [[https://arxiv.org/pdf/2006.04757.pdf][Language Modeling for Formal Mathematics]] ~ M. N. Rabe #LanguageModelling #Mathematics #TheoremProving

** Mayo 2020
#+html: <p align="center"><img src="wordClouds/mayo2020.png" /></p>

+ [[https://arxiv.org/pdf/1807.05520.pdf][Deep Clustering for Unsupervised Learning of Visual Features]] ~ M. Caron #UnsupervisedLearning #Clustering
+ [[https://towardsdatascience.com/illustrated-guide-to-transformer-cf6969ffa067][Illustrated Guide to Transformers]] ~ H. Jing #Transformers #NLP
+ [[https://mlinproduction.com/deploying-machine-learning-models/][The Ultimate Guide to Deploying Machine Learning Models]] ~ L. Patruno #Deployment #Series
+ [[https://arxiv.org/pdf/2005.09007.pdf][U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection]] ~ X. Qin #SalientObjectDetection
+ [[https://arxiv.org/abs/1912.02424][Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection]] ~ S. Zhang #ObjectDetection
+ [[https://medium.com/@deviparikh/how-we-write-rebuttals-dc84742fece1][How we write rebuttals]] ~ D. Parikh #Rebuttals #Advices
+ [[https://arxiv.org/abs/1710.09412][mixup: Beyond Empirical Risk Minimization]] ~ H. Zhang #ImageClassification #DataAugmentation
+ [[https://arxiv.org/abs/2005.12872][End-to-End Object Detection with Transformers]] ~ N. Carion #ObjectDetection #Transformers
+ [[https://arxiv.org/pdf/1711.11585.pdf][High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs]] ~ T-C. Wang #GANs #ImageSynthesis
+ [[https://arxiv.org/pdf/2005.10825.pdf][Instance-aware Image Colorization]] ~ J-w. Su #ImageColorisation #InstanceAware
+ [[https://www.youtube.com/watch?time_continue=1&v=l5he9JNJqHA&feature=emb_logo][A critical analysis of self-supervision, or what we can learn from a single image (Paper Explained)]]  ~ Y. Kilcher #SelfSupervision
+ [[https://arxiv.org/abs/1612.03242][StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks]] ~ H. Zhang #GANs #ImageSynthesis
+ [[https://arxiv.org/pdf/1811.04017.pdf!][A generic framework forprivacy preserving deep learning]] ~ A. Ryffel #Privacy #PySyft
+ [[https://github.com/OpenMined/PySyft/tree/master/examples/tutorials][Privacy Preserving Deep Learning with PyTorch & PySyft]] ~ PySyft #FederatedLearning #Privacy
+ [[http://papers.nips.cc/paper/6975-dynamic-routing-between-capsules.pdf][Dynamic Routing Between Capsules]] ~ S. Sabour #CapsuleNetworks #ComputerVision
+ [[https://arxiv.org/pdf/1604.06737.pdf][Entity Embeddings of Categorical Variables]] ~ C. Guo #Embeddings
+ [[https://arxiv.org/abs/1910.05895][Transformers without Tears: Improving the Normalization of Self-Attention]] ~ T. Nguyen #Transformers #NLP
+ [[https://arxiv.org/pdf/2005.10243.pdf][What Makes for Good Views for Contrastive Learning?]] ~ Y. Tian #ContrastiveLearning
+ [[https://www.nature.com/articles/s42003-020-0905-5.pdf][Training instance segmentation neural network with synthetic datasets for crop seed phenotyping]] ~ Y. Toda #Agriculture #Segmentation #SyntheticData
+ [[https://docs.google.com/presentation/d/1kSuQyW5DTnkVaZEjGYCkfOxvzCqGEFzWBy4e9Uedd9k/mobilepresent#slide=id.g168a3288f7_0_58][Machine Learning 101]] ~ J. Mayes #Introduction #DeepLearning #Slides
+ [[https://www.youtube.com/watch?v=p-zOeQCoG9c&t=41s][Weight Standardization (Paper Explained)]] ~ Y. Kilcher #Normalisation #DeepLearning #ParallelTraining 
+ [[https://arxiv.org/pdf/1807.03341.pdf][Troubling Trends in Machine Learning Scholarship]] ~ Z. C. Lipton #MachineLearning #Challenges
+ [[https://arxiv.org/pdf/2004.10605.pdf][Self-Supervised Representation Learning onDocument Images]] ~ A. Cosma #Documents #SelfSupervisedLearning #Classification 
+ [[https://www.youtube.com/watch?v=enXA0eghWQQ][Antipatterns in open source research code]] ~ J. Safi #AntiPatterns #OpenSource
+ [[https://www.youtube.com/watch?v=l_3zj6HeWUE&t=610s][Group Normalization (Paper Explained)]] ~ Y. Kilcher #Normalisation #DeepLearning #ParallelTraining 
+ [[https://keras.io/examples/][Keras code examples]] ~ Keras #Keras #Tutorials #ComputerVision #NLP #GANs #ReinforcementLearning
+ [[https://www.youtube.com/playlist?list=PLZbbT5o_s2xrfNyHZsM6ufI0iZENK9xgG][Neural Network Programming - Deep Learning with PyTorch]] ~ DeepLizard #Pytorch #Videos
+ [[https://theaisummer.com/gan-computer-vision/][GANs in computer vision: Introduction to generative learning]] ~ N. Adaloglou #GANs #Series
+ [[https://arxiv.org/abs/2004.14356][AxCell: Automatic Extraction of Results from Machine Learning Papers]] ~ A. Kardas #DataExtraction #TableDetection 
+ [[https://arxiv.org/pdf/2003.08505.pdf][A Metric Learning Reality Check]] ~ K. Musgrave #MetricLearning
+ [[https://arxiv.org/pdf/1909.13719.pdf][RandAugment: Practical automated data augmentationwith a reduced search space]] ~ E. Cubuk #DataAugmentation #ObjectDetection #ImageClassification #SemiSupervisedLearning
+ [[https://arxiv.org/pdf/2005.04757v1.pdf][A Simple Semi-Supervised Learning Framework for Object Detection]] ~ K. Sohn #SemiSupervisedLearning #ObjectDetection
+ [[https://www.theverge.com/2016/8/4/12369494/descartes-artificial-intelligence-crop-predictions-usda][This startup uses machine learning and satellite imagery to predict crop yields]] ~ A. Brokaw #Crops #Detection
+ [[https://arxiv.org/abs/2004.09927][TTNet: Real-time temporal and spatial video analysis of table tennis]] ~ Voeikov #Detection #Segmentation #Video #MultiTask
+ [[https://www.youtube.com/watch?v=G5lmya6eKtc][The future of NLP]] ~ HuggingFace #NLP #Youtube
+ [[https://medium.com/dair-ai/an-illustrated-guide-to-graph-neural-networks-d5564a551783][An Illustrated Guide to Graph Neural Networks]] ~ R. Anand #GraphNeuralNetworks
+ [[https://xiaohangzhan.github.io/projects/deocclusion/][Self-Supervised Scene De-occlusion]] ~ X. Zhan #SelfSupervisedLearning #Occlusion
+ [[https://sci-hub.tw/https://link.springer.com/article/10.1007/s11042-020-08929-z][Using off-the-shelf data-human interface platforms:traps and tricks]] ~ A. Angeli #Comparison #Orange #KNIME
+ [[https://arxiv.org/pdf/2004.14545.pdf][Explainable Deep Learning: A Field Guide for the Uninitiated]] ~ N. Xie #Explainable #Interpretability
+ [[https://arxiv.org/abs/2004.13453][DRU-net: An Efficient Deep Convolutional Neural Network for Medical Image Segmentation]] ~ M. Jafari #Segmentation #MedicalImaging
+ [[https://arxiv.org/abs/2004.15011][TLDR: Extreme Summarization of Scientific Documents]] ~ I. Cachola  #Summarization #NLP
+ [[https://github.com/Machine-Learning-Tokyo/Interactive_Tools][Interactive Tools for ML, DL and Math]] ~ S. Ilić #Visualization #InteractiveTools

** Abril 2020


#+html: <p align="center"><img src="wordClouds/abril2020.png" /></p>
+ [[https://arxiv.org/pdf/1905.00397.pdf][Fast AutoAugment]] ~ S. Lim #ImageAugmentation 
+ [[https://amitness.com/2020/03/fixmatch-semi-supervised/][The Illustrated FixMatch for Semi-Supervised Learning]] ~ A. Chaudhary #SemiSupervisedLearning #FixMatch
+ [[https://amitness.com/2020/04/recurrent-layers-keras/][A Visual Guide to Recurrent Layers in Keras]] ~ A. Chaudhary #NLP #RNN
+ [[https://github.com/ohmeow/blurr][An extensible integration of huggingface transformer models with fastai v2]] #NLP #FastAI #Transformers #Library 
+ [[https://www.mdpi.com/1999-4893/13/5/106/htm][Diagnosis in Tennis Serving Technique ]] ~ E. Roanes-Lozano #Tennis #GrobnerBasis #ComputerAlgebraSystem
+ [[https://arxiv.org/abs/2004.13060][GIMP-ML: Python Plugins for using Computer Vision Models in GIMP]] ~ K. Soman #Gimp #ComputerVision #DeepLearning
+ [[https://arxiv.org/pdf/2004.08686v1.pdf][A Large Dataset of Historical Japanese Documents with Complex Layouts]] ~ Z. Shen #Datasets #Documents
+ [[https://arxiv.org/abs/2004.11362][Supervised Contrastive Learning]] ~ P. Khosla #ContrastiveLearning #SemiSupervisedLearning #SelfSupervised
+ [[https://arxiv.org/pdf/2004.10934.pdf][YOLOv4: Optimal Speed and Accuracy of Object Detection]] ~ A. Bochkovskiy #YOLO #ObjectDetection
+ [[https://arxiv.org/pdf/1712.02950.pdf][CycleGAN, a Master of Steganography]] ~ C. Chu #GANs #Steganography
+ [[https://arxiv.org/pdf/2001.02522v1.pdf][On Interpretability of Artificial Neural Networks]] ~ F. Fan #Interpretability #NeuralNetworks #Survey
+ [[https://arxiv.org/abs/1911.11423][Single Headed Attention RNN: Stop Thinking With Your Head]] ~ S. Merity #RNNs #NLP
+ [[https://arxiv.org/abs/1912.01991][Self-Supervised Learning of Pretext-Invariant Representations]] ~ I. Misra #SelfSupervisedLearning 
+ [[https://arxiv.org/abs/1911.05722][Momentum Contrast for Unsupervised Visual Representation Learning]] ~ K. He #MoCO #RepresentationLearning #ContrastiveLearning #SelfSupervisedLearning 
+ [[https://arxiv.org/abs/1905.09272][Data-Efficient Image Recognition with Contrastive Predictive Coding]] ~ O. J. Henaff #ContrastiveLearning #SemiSupervisedLearning #SelfSupervisedLearning
+ [[https://arxiv.org/pdf/2002.12749.pdf][Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examples]] ~ P. Neekhara #DeepFakes #AdversarialExamples
+ [[https://colab.research.google.com/drive/1ZshwEPDDCHKZHkpmbVPvGoDEt1O1kICw#scrollTo=9-CMpP5a3Wcp][An end-to-end GAN example]] ~ F. Chollet #Keras2 #GANs
+ [[https://github.com/google/automl/tree/master/efficientdet][EfficientDet repository]] ~ M. Tan #ObjectDetection #EfficientDet
+ [[https://openai.com/blog/microscope/][OpenAI Microscope]] ~ L. Shubert #CNNs #Interpretability
+ [[https://deepai.org/publication/what-can-robotics-research-learn-from-computer-vision-research][What can robotics research learn from computer vision research?]] ~ P. Corke #Robotics #ComputerVision
+ [[https://lena-voita.github.io/posts/acl19_heads.html][The Story of Heads]] ~ L. Voita #Transformers #NLP
+ [[https://www.biorxiv.org/content/10.1101/740548v8][Deep Learning-Based Point-Scanning Super-Resolution Imaging]] ~ L. Fang #SuperResolution
+ [[https://towardsdatascience.com/can-we-generate-high-quality-movie-reviews-using-language-models-5158f494aea7][Can We Generate High-Quality Movie Reviews Using Language Models?]] ~ O. Dar #LanguajeModel #TextGeneration #NLP
+ [[https://medium.com/@lessw/meet-adamod-a-new-deep-learning-optimizer-with-memory-f01e831b80bd][Meet AdaMod: a new deep learning optimizer with memory]] ~ L. Wright #Optimiser
+ [[https://arxiv.org/abs/1606.02228][Systematic evaluation of CNN advances on the ImageNet]] ~ D. Mishkin #CNNs
+ [[http://karpathy.github.io/2019/04/25/recipe/][A Recipe for Training Neural Networks]] ~ A. Karpathy #NeuralNets #Recipes
+ [[https://arxiv.org/pdf/2001.07645v1.pdf][SAUNet: Shape Attentive U-Net for Interpretable Medical Image Segmentation]] ~ J. Sun #Segmentation #Interpretability
+ [[https://lena-voita.github.io/posts/emnlp19_evolution.html][Evolution of Representations in the Transformer]] ~ L. Voita #NLP #Transformers
+ [[https://arxiv.org/pdf/2001.09540v1.pdf][Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Inputs]] ~ M. Siam #Segmentation #Attention #FewShotLearning
+ [[https://jalammar.github.io/illustrated-transformer/][The Illustrated Transformer]] ~ J. Alamar #Transformers #NLP
+ [[https://jalammar.github.io/visualizing-neural-machine-translation-mechanics-of-seq2seq-models-with-attention/][Visualizing A Neural Machine Translation Model (Mechanics of Seq2seq Models With Attention)]] ~ J. Alammar #Attention #NLP
+ [[https://www.pyimagesearch.com/2020/04/13/opencv-age-detection-with-deep-learning/][OpenCV Age Detection with Deep Learning]] ~ A. Rosenbrog #PyimageSearch #AgeDetection #ImageClassification
+ [[https://arxiv.org/pdf/2004.02042v1.pdf][ObjectNet Dataset: Reanalysis and Correction]] ~ A. Borji #ObjectNet #ObjectDetection
+ [[http://brohrer.github.io/how_convolutional_neural_networks_work.html][How do Convolutional Neural Networks work?]] ~ B. Rohrer #IntroCNNs 
+ [[https://arxiv.org/pdf/2001.03994.pdf][FAST IS BETTER THAN FREE:REVISITING ADVERSARIAL TRAINING]] ~ E. Wong #AdeversarialTraining
+ [[https://arxiv.org/pdf/1904.13000.pdf][Adversarial Training and Robustness for Multiple Perturbations]] ~ F. Tramèr #AdeversarialTraining #TrabajoSevilla
+ [[https://deepai.org/publication/examining-the-benefits-of-capsule-neural-networks][Examining the Benefits of Capsule Neural Networks]] ~ A. Punjabi #CapsuleNetworks #Explainability
+ [[https://arxiv.org/pdf/1909.06674.pdf][A Step Toward Quantifying IndependentlyReproducible Machine Learning Research]] ~ E. Raff #Reproducibility
+ [[https://arxiv.org/pdf/2004.01241v1.pdf][Semantic Segmentation of Underwater Imagery: Dataset and Benchmark]] ~ J. Islam #SemanticSegmentation #Dataset
+ [[https://research.fb.com/wp-content/uploads/2020/02/The-Architectural-Implications-of-Facebook%E2%80%99s-DNN-based-Personalized-Recommendation.pdf][The Architectural Implications of Facebook’sDNN-based Personalized Recommendation]] ~ U. Gupta #RecommendationSystems 
+ [[https://jalammar.github.io/illustrated-bert/][The Illustrated BERT, ELMo, and co. (How NLP Cracked Transfer Learning)]] ~ J. Alammar #NLP
+ [[http://www.cleverhans.io/][cleverhans blog]] ~ I. GodFellow #Blog #Security #MachineLearning
+ [[http://www.cleverhans.io/2020/04/06/stealing-bert.html][How to steal modern NLP systems with gibberish?]] ~ K. Krishna #NLP #Bert #Attacks #Distillation
+ [[https://colab.research.google.com/drive/1VJzTxN1QYXdc9LOjVO4DWqpV7nY4okmD#scrollTo=PwZ1zOxil56y][Text Similarity Search with Modern NLP and Elasticsearch Service]] #ElasticSearch #NLP
+ [[https://arxiv.org/pdf/2003.13853v1.pdf][Semi-supervised Learning for Few-shot Image-to-Image Translation]] ~ Y. Wan #SemiSupervisedLearning #Image2Image
+ [[https://arxiv.org/pdf/1805.08318.pdf][Self-Attention Generative Adversarial Networks]] ~ H. Zhang #Attention #GANs
+ [[https://arxiv.org/pdf/1904.11486.pdf][Making Convolutional Networks Shift-Invariant Again]] ~ R. Zhang #ConvolutionalNeuralNetworks #Antialiasing
+ [[https://arxiv.org/abs/2004.01180][Learning to See Through Obstructions]] ~ Y. Liu #ObstructionRemoval
+ [[https://arxiv.org/pdf/1708.07860.pdf][Multi-task Self-Supervised Visual Learning]] ~ C. Doersch #SelfSupervisedLearning #MultiTaskLearning
+ [[https://www.pyimagesearch.com/2020/04/06/blur-and-anonymize-faces-with-opencv-and-python/][Blur and anonymize faces with OpenCV and Python]] ~ A. Rosenbrog #Pyimagesearch #FaceDetection
+ [[https://arxiv.org/pdf/2002.11829.pdf][Representation Learning Through Latent Canonicalizations]] ~ O. Litani #RepresentationLearning #SelfSupervisedLearning
+ [[https://arxiv.org/pdf/2003.11734.pdf][Fastidious Attention Network for Navel Orange Segmentation]] ~ S. Xiaoye #SemanticSegmentation #Attention
+ [[https://arxiv.org/pdf/1804.01622.pdf][Image Generation from Scene Graphs]] ~ J. Johnson #ImageGeneration #SceneGraphs
+ [[https://arxiv.org/pdf/1604.07379.pdf][Context Encoders: Feature Learning by Inpainting]] ~ Pathak #InPainting #AutoEncoders
+ [[https://www.pyimagesearch.com/2020/03/30/autoencoders-for-content-based-image-retrieval-with-keras-and-tensorflow/][Autoencoders for Content-based Image Retrieval with Keras and TensorFlow]] ~ A. Rosenbrog #PyimageSearch #AutoEncoders #ImageRetrieval
+ [[https://arxiv.org/pdf/2003.11303v1.pdf][Cylindrical Convolutional Networks forJoint Object Detection and Viewpoint Estimation]] ~ S. Joung #ObjectDetection #3DConvolutions
+ [[http://openaccess.thecvf.com/content_ICCV_2019/papers/Liu_Generative_Modeling_for_Small-Data_Object_Detection_ICCV_2019_paper.pdf][Generative Modeling for Small-Data Object Detection]] ~ L. Liu #ObjectDetection #GAN

** Marzo 2020

#+html: <p align="center"><img src="wordClouds/marzo2020.png" /></p>
+ [[http://www.vision-ary.net/2015/03/largest-boosted-cascades-opencv-lbp-haar-hog/][HAAR LBP HOG Cascades for OpenCV]] ~ Vision-Ary Team #ObjectDetection
+ [[https://link.springer.com/content/pdf/10.1007/s11263-020-01300-7.pdf][Layout2image: Image Generation from Layout]] ~ B. Zhao #Layout2Image
+ [[https://www.youtube.com/watch?v=egs0XN-xjA0&list=PL_lsbAsL_o2BY-RrqVDKDcywKnuUTp-f3&index=13%3Futm_source%3D-twitter&utm_medium=PyTorch&utm_campaign=organic&utm_content=post-url&utm_offering=pytorch-devcon19&utm_product=Detectron2][Detectron2 - Next Gen Object Detection Library]] ~ Y. Wu #Detectron #ObjectDetection #Video
+ [[https://arxiv.org/pdf/2003.11571v1.pdf][Learning Layout and Style Reconfigurable GANsfor Controllable Image Synthesis]] ~ W. Sun #GANs #Layout2Image
+ [[https://www.youtube.com/watch?v=bGEDjhbSHmg][Introduction to Semi-supervised Learning using MixMatch]] ~ R. Löwenström #SemiSupervisedLearning #MixMatch
+ [[https://arxiv.org/pdf/1805.08318.pdf][Self-Attention Generative Adversarial Networks]] ~ H. Zhang #Attention #GANs
+ [[https://arxiv.org/pdf/1908.08681v1.pdf][Mish: A Self Regularized Non-Monotonic Neural Activation Function]] ~ D. Misra #ActivationFunction
+ [[https://ipam.wistia.com/medias/w1ii9wdqnd][From classical statistics to modern machine learning]] ~ M. Belkin #DoubleDescent
+ [[https://www.youtube.com/watch?v=MX5cqgUVkQE][How to Know]] ~ C. Kidd #Neuropsycology #Learning
+ [[https://towardsdatascience.com/tsne-vs-umap-global-structure-4d8045acba17][tSNE vs. UMAP: Global Structure]] ~ N. Oskolkov #DimensionalityReduction
+ [[https://github.com/AntixK/PyTorch-VAE][PyTorch VAE]] ~ A. K. Subramanian #Pytorch #VAE
+ [[https://skellig-ai.github.io/2020/02/03/The-Augmented-Scientist-Part-1.html][The Augmented Scientist Part 1: Practical Application Machine Learning in Classification of SEM Images]] ~ I. Keaney #ImageClassification #FastAI
+ [[https://arxiv.org/pdf/2001.07626.pdf][PatchPerPix for Instance Segmentation]] ~ P. Hirsch #InstanceSegmentation #Datasets 
+ [[https://github.com/muellerzr/Practical-Deep-Learning-for-Coders-2.0][A walk with FastAI 2]] ~ Muellerzr #FastaAI #Course
+ [[https://people.eecs.berkeley.edu/~tinghuiz/projects/SfMLearner/cvpr17_sfm_final.pdf][Unsupervised Learning of Depth and Ego-Motion from Video]] ~ T. Zhou #SelfSupervisedLearning #Video 
+ [[https://arxiv.org/abs/2003.10580][Meta Pseudo Labels]] ~ H. Pham #SelfSupervisedLearning #SemiSupervisedLearning
+ [[https://www.tensorflow.org/quantum][TensorFlow Quantum is a library for hybrid quantum-classical machine learning]] ~ Tensorflow #QuantumMachineLearning
+ [[https://www.thelancet.com/journals/landig/article/PIIS2589-7500(20)30003-0/fulltext][Changes in cancer detection and false-positive recall in mammography using artificial intelligence: a retrospective, multireader study]] ~ H. Kim #MedicalImaging #ImageClassification
+ [[https://arxiv.org/pdf/2002.01612v1.pdf][Generating Interpretable Poverty Maps using Object Detection in Satellite Images]] ~ K. Ayush #ObjectDetection #YOLO
+ [[https://arxiv.org/abs/2002.02405][How Good is the Bayes Posterior in Deep Neural Networks Really?]] ~ F. Wenzel #BayesianInference
+ [[https://arxiv.org/pdf/1901.03407.pdf][Deep learning for anomaly detection: a survey]] ~ R. Chalapathy #AnomalyDetection
+ [[https://arxiv.org/pdf/2002.07772v1.pdf][The Tree Ensemble Layer: Differentiability meets Conditional Computation]] ~ H. Hazimeh #DecissionTrees #EnsembleLayer
+ [[https://www.nature.com/articles/s41598-020-61055-6][AppendiXNet: Deep Learning for Diagnosis of Appendicitis from A Small Dataset of CT Exams Using Video Pretraining]] ~ P. Rajpurkar #MedicalImaging #3DClassification #TransferLearning
+ [[https://arxiv.org/pdf/1904.11490.pdf][RepPoints: Point Set Representation for Object Detection]] ~ Z. Yang #ObjectDetection
+ [[https://arxiv.org/pdf/1902.04103.pdf][Bag of Freebies for Training Object Detection Neural Networks]] ~ Z. Zhang #ObjectDetection #Tricks
+ [[https://ruder.io/semi-supervised/][An overview of proxy-label approaches for semi-supervised learning]] ~ S. Ruder #SemiSupervisedLearning #ProxyLabel
+ [[https://github.com/noachr/MixMatch-fastai/blob/master/MixMatch%20Blog.ipynb][A fastai/Pytorch implementation of MixMatch]] ~ N. Rubinstein #FastAI #MixMatch #SemiSupervisedLearning
+ [[https://ai.facebook.com/blog/ccmatrix-a-billion-scale-bitext-data-set-for-training-translation-models/][CCMatrix: A billion-scale bitext data set for training translation models]] ~ H. Schwenk #NLP #Dataset #Translation
+ [[https://deepai.org/publication/incremental-object-detection-via-meta-learning][Incremental Object Detection via Meta-Learning]] ~ K. J. Joseph #ObjectDetection #MetaLearning
+ [[https://arxiv.org/pdf/1906.06423.pdf][Fixing the train-test resolution discrepancy]] ~ H. Touvron #ImageNet #Classification #FixRes
+ [[https://arxiv.org/pdf/2003.08237.pdf][Fixing the train-test resolution discrepancy: FixEfficientNet]] ~ H. Touvron #Classification #FixEfficientNet #ImageNet
+ [[https://arxiv.org/pdf/1805.04574.pdf][Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation]] ~ Y. Wei #WeakLearning #SemiSupervisedLearning
+ [[https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Papandreou_Weakly-_and_Semi-Supervised_ICCV_2015_paper.pdf][Weakly- and Semi-Supervised Learning of a Deep Convolutional Network forSemantic Image Segmentation]] ~ G. Papandreou #WeakLearning #SemiSupervisedLearning
+ [[https://arxiv.org/pdf/1808.03575.pdf][Weakly- and Semi-Supervised Panoptic Segmentation]] ~ Q. Li #SemanticSegmentation #WeakLearning #PanopticSegmentation
+ [[https://sci-hub.tw/10.1145/3097983.3098135][Learning from multiple teacher network]] ~ S. You #MultipleTeacher #DeepLearning #Distillation
+ [[https://arxiv.org/pdf/2003.08462v1.pdf][Semi-supervised few-shot learning for medicalimage segmentation]] ~ A. Fayjie #SemiSupervisedLearning #FewShotLearning
+ [[https://arxiv.org/pdf/2002.05709.pdf][A Simple Framework for Contrastive Learning of Visual Representations]] ~ T. Chen #ContrastiveLearning 
+ [[https://ai.googleblog.com/2020/03/visual-transfer-learning-for-robotic.html][Visual Transfer Learning for Robotic Manipulation]] ~ Y-C. Lin #Robotics #TransferLearning 
+ [[https://arxiv.org/abs/2003.06798][StarNet: towards weakly supervised few-shot detection and explainable few-shot classification]] ~ L. Karlinsky #FewShotLearning #Interpretability #WeaklySupervised #ObjectDetection
+ [[http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhou_Collaborative_Learning_of_Semi-Supervised_Segmentation_and_Classification_for_Medical_Images_CVPR_2019_paper.pdf][Collaborative Learning of Semi-Supervised Segmentation and Classification forMedical Images]] ~ Y. Zhou #CollaborativeLearning #Segmentation #Classification #MedicalImaging
+ [[https://www.fast.ai/2020/02/13/fastai-A-Layered-API-for-Deep-Learning/][fastai—A Layered API for Deep Learning]] ~ J. Howard #FastAI
+ [[https://github.com/earthspecies/from_zero_to_DSP][From Zero to DSP]] ~ radekosmulski #Audio
+ [[https://insightsimaging.springeropen.com/articles/10.1186/s13244-019-0832-5#Tab1][Deep learning workflow in radiology: a primer]] ~ E. Montagnon #DeepLearning #MedicalImaging #Workflow
+ [[https://arxiv.org/abs/2002.04803][Machine Learning in Python: Main developments and technology trends in data science, machine learning, and artificial intelligence]] ~ S. Raschka #Python #MachineLearning #DeepLearning
+ [[https://arxiv.org/pdf/2002.02948.pdf][A deep-learning view of chemical space designed to facilitate drug discovery]] ~ P. Maragakis #Chemistry #DrugDiscovery
+ [[https://arxiv.org/pdf/2002.01155v1.pdf][Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception]] ~ J. Islam #SuperResolution #ImageEnhancement
+ [[https://medium.com/huggingface/from-zero-to-research-an-introduction-to-meta-learning-8e16e677f78a][From zero to research — An introduction to Meta-learning]] ~ T. Wolf #MetaLearning
+ [[https://arxiv.org/abs/1908.00709][AutoML: A Survey of the State-of-the-Art]] ~ X. He #AutoML
+ [[https://www.cc.gatech.edu/~parikh/citizenofcvpr/][Good Citizien of CVPR]] ~ Conference #Research #Advices
+ [[https://colab.research.google.com/gist/pablo14/857e3259b441621f9cba194bf272c492/tutorial-on-spam-detection-using-fastai-ulmfit-part-2-classification-model.ipynb][Tutorial on SPAM detection using fastai ULMFiT - Part 2: Classification Model]] ~ P. Casas #ULMFit #FastAI #NLP
+ [[https://www.biorxiv.org/content/10.1101/2020.02.20.956268v1.full.pdf][Interactive machine learning for fast and robust cell profiling]] ~ L. Laux #Segmentation #CellProfiler
+ [[https://arxiv.org/pdf/2003.01383v1.pdf][Fully Convolutional Networks for Automatically Generating Image Masks to Train Mask R-CNN]] ~ H. Wu #ObjectDetection 
+ [[https://github.com/huggingface/transformers/tree/master/notebooks][Transformers Notebooks]] ~ HuggingFace #NLP #Transformers
+ [[https://github.com/mogwai/fastai_audio][Fast AI Audio]] ~ Mogwai #FastAI #Audio
+ [[https://www.kaggle.com/c/rsna-intracranial-hemorrhage-detection/discussion/114214][RSNA Intracranial Hemorrhage Detection FastAI]] ~ J. Howard #MedicalImaging #FastAI
+ [[https://machinelearningmastery.com/framework-for-imbalanced-classification-projects/][Step-By-Step Framework for Imbalanced Classification Projects]] ~ J. Brownlee #ImageClassification #ImbalancedDatasets
+ [[https://www.pyimagesearch.com/2020/03/09/grad-cam-visualize-class-activation-maps-with-keras-tensorflow-and-deep-learning/][Grad-CAM: Visualize class activation maps with Keras, TensorFlow, and Deep Learning]] ~ A. Rosenbrog #PyimageSearch #ActivationMaps #Interpretability
+ [[https://arxiv.org/pdf/2003.06957.pdf][Frustratingly Simple Few-Shot Object Detection]] ~ X. Wang #ObjectDetection #FewShotLearning [[https://github.com/ucbdrive/few-shot-object-detection][Repositorio]]
+ [[https://arxiv.org/pdf/1904.04445.pdf][Semi-Supervised Segmentation of Salt Bodies inSeismic Images using an Ensemble ofConvolutional Neural Networks]] ~ Y. Babakhin #SemiSupervisedLearning #SemanticSegmentation #SelfLearning
+ [[https://www.pyimagesearch.com/2020/03/16/detecting-covid-19-in-x-ray-images-with-keras-tensorflow-and-deep-learning/][Detecting COVID-19 in X-ray images with Keras, TensorFlow, and Deep Learning]] ~ A. Rosenbrog #PyimageSearch #ImageClassification
+ [[https://gitmemory.com/issue/AlexeyAB/darknet/2746/477459452][mAP (mean average precision) calculation for different Datasets ]] ~ AlexeyAB #Detection #Metrics #YOLO
+ [[https://arxiv.org/abs/1911.04252][Self-training with Noisy Student improves ImageNet classification]] ~ Q. Xie #SelfSupervised #SemiSupervised
+ [[https://forums.fast.ai/t/fastai-v2-has-a-medical-imaging-submodule/56117][Fastai v2 has a medical imaging submodule!]] ~ J. Howard #FastAI #MedicalData
+ [[https://www.microsoft.com/en-us/research/blog/zero-deepspeed-new-system-optimizations-enable-training-models-with-over-100-billion-parameters/?OCID=msr_blog_zerodeep_tw][ZeRO & DeepSpeed: New system optimizations enable training models with over 100 billion parameters]] ~ DeepSpeed #LargeModels #Library #ModelTraining #Parallelism
+ [[https://speakerdeck.com/inesmontani/the-future-of-nlp-in-python-keynote-pycon-colombia-2020][The future of NLP in Python]] ~ I. Montani #NLP
+ [[https://quantum-journal.org/papers/q-2020-02-06-226/][Data re-uploading for a universal quantum classifier]] ~ A. Pérez-Salinas #QuantumComputing #MachineLearning
+ [[https://ai.googleblog.com/2020/03/announcing-tensorflow-quantum-open.html][Announcing TensorFlow Quantum: An Open Source Library for Quantum Machine Learning ]] ~ A. Ho #QuantumComputing #MachineLearning
+ [[https://github.com/alhassy/PythonCheatSheet][PythonCheatSheet]] ~ [[https://github.com/alhassy][alhassy]] #Python
+ [[https://distill.pub/2020/circuits/zoom-in/][Zoom In: An Introduction to Circuits]] ~ C. Olah #Interpretability 
+ [[https://ai.googleblog.com/2020/03/fast-and-easy-infinitely-wide-networks.html][Fast and Easy Infinitely Wide Networks with Neural Tangents]] ~ S. Schoenholz #InfiniteNetworks #NeuralTangents
+ [[https://arxiv.org/abs/2002.05709][A Simple Framework for Contrastive Learning of Visual Representations]] ~ T. Chen #ContrastiveLearning #SelfSupervisedLearning #DataAugmentation
+ [[https://arxiv.org/pdf/1905.13538.pdf][FUNSD: A Dataset for Form Understandingin Noisy Scanned Documents]] ~ G. Jaume #FormUnderstanding #Dataset #Athento [[https://guillaumejaume.github.io/FUNSD/download/][Repositorio]]
+ [[https://arxiv.org/pdf/1908.07836.pdf][PubLayNet: largest dataset ever for documentlayout analysis]] ~ X. Zhong #LayoutAnalysis #TableDetection #Dataset #Athento [[https://dax.cdn.appdomain.cloud/dax-publaynet/1.0.0/PubLayNet.html][Repositorio]]
+ [[https://arxiv.org/pdf/1911.09070.pdf][EfficientDet: Scalable and Efficient Object Detection]] ~ M. Tan #ObjectDetection #EfficientDet #Efficiency
+ [[https://arxiv.org/abs/1911.11929][CSPNet: A New Backbone that can Enhance Learning Capability of CNN]] ~ C. Hang #YOLO #ObjectDetection #Darknet #Efficient [[https://github.com/WongKinYiu/CrossStagePartialNetworks][Repositorio]]
+ [[https://arxiv.org/pdf/1904.12848.pdf][Unsupervised data augmentation for consistency training]] ~ Q. Xie #SemiSupervisedLearning #DataAugmentation
+ [[https://drive.google.com/file/d/1ax1-XprJHDRRv2Ru3dJwPLs3ShxcpQ3r/view][Learning from unlabeled data]] ~ T. Luong #SelfSupervisedLearning #SemiSupervisedLearning #NoisyStudent
+ [[https://arxiv.org/abs/2002.08512][Reliance on Metrics is a Fundamental Challenge for AI]] ~ R. Thomas #Ethics 
+ [[https://github.com/OpenMined/PySyft/tree/master/examples/tutorials/translations/espa%C3%B1ol][Pysyft:  A library for encrypted, privacy preserving machine learning]] ~ Pysyft #Privacy #DeepLearning
+ [[https://github.com/Machine-Learning-Tokyo/AI_Curriculum][AI Curriculum]] ~ Suzana Ilić #DeepLearning #Courses #NLP #ComputerVision
+ [[https://www.si.edu/openaccess/faq][Smithsonian Open Access]] #Datasets #Images #Museums
+ [[https://www.sciencedirect.com/science/article/pii/S2452310017300537][The imaging tsunami: Computational opportunities and challenges]] ~ W. Ouyang #Microscopy #Bioimaging #SuperResolution
+ [[https://github.com/fastai/fastbook][Draft of the fastai book]] ~ J. Howard #FastAI #Deeplearning #NLP #ComputerVision
+ [[https://amitness.com/2020/02/illustrated-self-supervised-learning/][The Illustrated Self-Supervised Learning]] ~ A. Chaudhary #SelfSupervisedLearning
+ [[https://www.sciencedirect.com/science/article/pii/S0092867420301021?via%3Dihub][A Deep Learning Approach to Antibiotic Discovery]] ~ J. M. Stokes #Antibiotics #DeepLearning
+ [[https://towardsdatascience.com/a-keras-based-autoencoder-for-anomaly-detection-in-sequences-75337eaed0e5][A Keras-Based Autoencoder for Anomaly Detection in Sequences]] ~ A. Agmon #AnomalyDetection #AutoEncoders #SequenceData
+ [[https://www.pyimagesearch.com/2020/03/02/anomaly-detection-with-keras-tensorflow-and-deep-learning/][Anomaly detection with Keras, TensorFlow, and Deep Learning]] ~ A. Rosebrock #PyimageSearch #AnomalyDetection #AutoEncoders
+ [[https://github.com/ctgk/PRML][Jupyter notebooks Bishop's book]] ~ #MachineLearning #BishopBook

** Febrero 2020

+ [[https://medium.com/bethgelab/increasing-the-robustness-of-dnns-against-image-corruptions-by-playing-the-game-of-noise-4566b5c2c8d5][A surprisingly simple way to make DNNs robust against many types of image corruptions]] ~ E. Rusak #DataAugmentation #Robustness #GaussianNoise
+ [[https://arxiv.org/pdf/2001.11202v1.pdf][Image Embedded Segmentation: Combining Supervised and Unsupervised Objectives through Generative Adversarial Networks]] ~ C. Taylan #GANs #SemanticSegmentation #Image2Image
+ [[https://arxiv.org/pdf/2001.10585v1.pdf][An Automated Approach for the Discovery of Interoperability]] ~ D. Sap #Interoperability #CAD


** Enero 2020

#+html: <p align="center"><img src="wordClouds/enero2020.png" /></p>
+ [[https://arxiv.org/abs/1911.05722][Momentum Contrast for Unsupervised Visual Representation Learning]] ~ K. He #RepresentationLearning #ContrastiveLearning #SelfSupervisedLearning 
+ [[https://ankeshanand.com/blog/2020/01/26/contrative-self-supervised-learning.html][Contrastive Self-Supervised Learning]] ~ A. Anand #ContrastiveLearning #SemiSupervisedLearning
+ [[https://www.pyimagesearch.com/2020/01/27/yolo-and-tiny-yolo-object-detection-on-the-raspberry-pi-and-movidius-ncs/][YOLO and Tiny-YOLO object detection on the Raspberry Pi and Movidius NCS]] ~ A. Rosebrock #PyimageSearch #YOLO #RaspberriPI
+ [[https://arxiv.org/pdf/1801.06146.pdf][Universal Language Model Fine-tuning for Text Classification]] ~ J. Howard #ULMFit #NaturalLanguageProcessing #FineTuning
+ [[https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7839189&tag=1][Beyond a Gaussian Denoiser: Residual Learningof Deep CNN for Image Denoising]] ~ K. Zhang #Denoising #CNNs
+ [[https://arxiv.org/pdf/1805.08318.pdf][Self-Attention Generative Adversarial Networks]] ~ H. Zhang #GANs #Attention
+ [[https://www.fast.ai/2019/05/03/decrappify/][Decrappification, DeOldification, and Super Resolution]] ~ J. Howard #SuperResolution #ImageColorisation #GANs #Unet
+ [[https://papers.nips.cc/paper/9259-consistency-based-semi-supervised-learning-for-object-detection.pdf][Consistency-based Semi-supervised Learning forObject Detection]] ~ J. Jeong #SemiSupervisedLearning #ObjectDetection
+ [[https://arxiv.org/abs/2001.07685][FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence]] ~ K. Sohn #SemiSupervisedLearning #ImageClassification
+ [[http://jbcordonnier.com/posts/attention-cnn/][How a self-attention layer can learn convolutional filters?]] ~ J-B. Cordonnier #Attention #ConvolutionalNeuralNetworks
+ [[https://ieeexplore.ieee.org/abstract/document/8843852][Unsupervised Exemplar-Based Learning for Improved Document Image Classification]] ~ S. Abuelwafa #DocumentImageClassification #SemiSupervisedLearning
+ [[https://www.biorxiv.org/content/10.1101/622803v1.full.pdf+html][Biological Structure and Function Emerge from Scaling Unsupervised Learning to 250 Million Protein Sequences]] ~ A. Rives #Proteins #SelfSupervision
+ [[https://chemrxiv.org/articles/Inductive_Transfer_Learning_for_Molecular_Activity_Prediction_Next-Gen_QSAR_Models_with_MolPMoFiT/9978743/1][Inductive Transfer Learning for Molecular Activity]] ~ X. Li #ULMFiT #Chemistry
+ [[https://colah.github.io/posts/2015-08-Understanding-LSTMs/][Understanding LSTM Networks]] ~ C. Olah #RecurrentNeuralNetworks #NaturalLanguageProcessing 
+ [[https://github.com/nstrodt/UDSMProt][UDSMProt: Universal Deep Sequence Models for Protein Classification]] ~ N. Strodthoff #ULMFiT #ProteinClassification
+ [[https://github.com/kheyer/Genomic-ULMFiT][Genomic ULMFiT]] ~ K. Heyer #ULMFiT #Genomics
+ [[https://www.pyimagesearch.com/2020/01/20/intro-to-anomaly-detection-with-opencv-computer-vision-and-scikit-learn/][Intro to anomaly detection with OpenCV, Computer Vision, and scikit-learn]] ~ A. Rosebrock #AnomalyOutlierDetection #IsolationForest
+ [[https://ai.googleblog.com/2020/01/reformer-efficient-transformer.html][Reformer: The Efficient Transformer]] ~ N. Kitaev #Attention #SequenceModels
+ [[https://text-machine-lab.github.io/blog/2020/bert-secrets/][The Dark Secrets of BERT]] ~ A. Rogers #NaturalLanguageProcessing #BERT
+ [[https://arxiv.org/pdf/1902.07208.pdf][Transfusion: Understanding Transfer Learning forMedical Imaging]] ~ M. Raghu #TransferLearning #MedicalImaging
+ [[https://nlp.fast.ai/classification/2018/05/15/introducing-ulmfit.html][Introducing state of the art text classification with universal language models]] ~ J. Howard #NaturalLanguageProcessing #SemiSupervisedLearning #ULMFiT
+ [[https://arxiv.org/pdf/1902.06162.pdf][Self-supervised Visual Feature Learning withDeep Neural Networks: A Survey]] ~ L. Jing  #SemiSupervisedLearning #SelfSupervisedLearning #PretextTasks #Survey
+ [[https://www.fast.ai/2020/01/13/self_supervised/][Self-supervised learning and computer vision]] ~ J. Howard #SemiSupervisedLearning #SelfSupervisedLearning #PretextTasks
+ [[https://www.cell.com/cell/fulltext/S0092-8674(18)30154-5][Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning]] ~ D. S. Kermany #TransferLearning #MedicalImaging
+ [[https://ruder.io/research-highlights-2019/][10 ML & NLP Research Highlights of 2019]] ~ S. Ruder #NaturalLanguageProcessing #Highlights
+ [[https://www.aaai.org/ojs/index.php/AAAI/article/view/4330][Towards Automated Semi-Supervised Learning]] ~ Y-F. Li #AutoML #SemiSupervisedLearning #StructuredData
+ [[https://www.fast.ai/2020/01/07/data-questionnaire/][Data project checklist]] ~ J. Howard #DataScience 
+ [[https://www.fast.ai/2019/07/08/fastai-nlp/][A Code-First Introduction to Natural Language Processing]] ~ R. Thomas #NaturalLanguageProcessing #Course
+ [[https://arxiv.org/pdf/1903.09731.pdf][Expert-Augmented Machine Learning]] ~ E. D. Gennatas #ExpertKnowledge
+ [[https://arxiv.org/abs/1908.09715][City-Scale Road Extraction from Satellite Imagery v2: Road Speeds and Travel Times]] ~ A. Van Etten #OpenStreetMap #RoadExtraction #SemanticSegmentation 
+ [[https://arxiv.org/abs/1904.13000][Adversarial Training and Robustness for Multiple Perturbations]] ~ F. Tramer #AdversialAttacks #Defenses
+ [[https://arxiv.org/abs/1909.00015][Adaptively Sparse Transformers]] ~ G. M. Correia #NaturalLanguageProcessing #Attention #Transformers
+ [[https://arxiv.org/abs/1910.04302][Prescribed Generative Adversarial Networks]] ~ A. B. Dieng #GANs 
+ [[https://arxiv.org/abs/1912.11975][Clinical XLNet: Modeling Sequential Clinical Notes and Predicting Prolonged Mechanical Ventilation]] ~ K. Huang #ClinicalData #HealthCare #NaturalLanguageProcessing 
+ [[https://arxiv.org/pdf/1912.13213.pdf][A Modern Introduction to Online Learning]] ~ F. Orabona #OnlineLearning
+ [[https://osf.io/mkzcq/][Hyper-Kvasir: A Comprehensive Multi-Class Image and Video Dataset for Gastrointestinal Endoscopy]] ~ H. Borgli #Datasets #ImageClassification #SemanticSegmentation
+ [[https://ieeexplore.ieee.org/abstract/document/8580569][Development of Algorithms for Automated Detection of Cervical Pre-Cancers With a Low-Cost, Point-of-Care, Pocket Colposcope]] ~ M. Nyamewaa Asiedu #MedicalImaging #LowResources
+ [[https://arxiv.org/pdf/1912.05752.pdf][The Use of Deep Learning for Symbolic IntegrationA Review of (Lample and Charton, 2019)]] ~ E. Davis #DeepLearning #ComputerAlgebraSystems #Review
+ [[https://medium.com/@the_change/linear-algebra-is-fun-trust-me-part-1-dfab83c2453e][Linear Algebra is fun, trust me!]] ~ S. Sharma #LinearAlgebra #Maths #Applications
+ [[https://blog.google/technology/health/improving-breast-cancer-screening][Using AI to improve breast cancer screening]] ~ S. Shetty #MedicalImaging #Support #Health

** Diciembre 2019
#+html: <p align="center"><img src="wordClouds/diciembre2019.png" /></p>

+ [[https://www.pyimagesearch.com/2019/12/30/label-smoothing-with-keras-tensorflow-and-deep-learning/][Label Smoothing with Keras and Tensorflow]] A. Rosebrock #PyimageSearch #LabelSmoothing #Regularisation
+ [[https://st2.ning.com/topology/rest/1.0/file/get/1211570060?profile=original][Data Science Cheatsheet]] ~ M. Lin #DataScience
+ [[https://www.analyticsvidhya.com/blog/2019/02/building-crowd-counting-model-python/?utm_source=linkedin.com&utm_medium=social][It’s a Record-Breaking Crowd]] ~ P. Sharma #CroudCounting #Tutorial
+ [[http://blizzard.cs.uwaterloo.ca/keshav/home/Papers/data/07/paper-reading.pdf][How to Read a Paper]] ~ S. Keshav #Methods #Research #Reading 
+ [[https://arxiv.org/pdf/1901.02985.pdf][Auto-DeepLab:Hierarchical Neural Architecture Search for Semantic Image Segmentation]] ~ C. Liu #SemanticSegmentation #NeuralArchitectureSearch
+ [[https://blog.datascienceheroes.com/spam-detection-using-fastai-ulmfit-part-1-language-model/][SPAM detection using fastai ULMFiT]] ~ P. Casas #FastAI #NaturalLanguageProcessing #SpamDetection
+ [[https://distill.pub/2016/augmented-rnns/][Attention and Augmented Recurrent Neural Networks]] ~ C. Olah #NaturalLanguageProcessing #Attention #RNNs
+ [[https://arxiv.org/pdf/1912.10077v1.pdf][Are Transformers universal approximators of sequence-to-sequence functions?]] ~ C. Yun #NaturalLanguageProcessing #Transformers #Attention #ContextualMapping
+ [[https://arxiv.org/pdf/1812.05239.pdf][Improving Fairness in Machine Learning Systems:What Do Industry Practitioners Need?]] ~ K. Holstein #Fairness #Industry #HumanComputerInteraction
+ [[https://retina.elpais.com/retina/2019/12/17/innovacion/1576572302_779289.html][Nike patenta unas zapatillas basadas en ‘blockchain’]] ~ J. Cortes #Blockchain #Falsificaciones
+ [[https://lukeoakdenrayner.wordpress.com/2019/10/14/improving-medical-ai-safety-by-addressing-hidden-stratification/][Improving Medical AI Safety by Addressing Hidden Stratification]]  ~ L. Oakden-Rayner  #MedicalAI #Methods
+ [[https://lukeoakdenrayner.wordpress.com/2019/06/01/the-best-medical-ai-research-that-you-probably-havent-heard-of/][The best medical AI research (that you probably haven’t heard of)]] ~ L. Oakden-Rayner #ClinicalTrials #MedicalAI
+ [[https://github.com/MIC-DKFZ/medicaldetectiontoolkit][Medical Detection Toolkit]] ~ P. Jaeger #ObjectDetection #Software
+ [[https://towardsdatascience.com/a-new-way-to-look-at-gans-7c6b6e6e9737][A New Way to look at GANs]] ~ M. Pasini #GANs #SiameseNetworks
+ [[https://www.biorxiv.org/content/10.1101/589333v1][Unified rational protein engineering with sequence-based deep representation learning]] ~ E. Alley #Chemistry
+ [[https://www.blog.google/products/search/search-language-understanding-bert][Understanding searches better than ever before]] ~ P. Nayak #NaturalLanguageProcessing #BERT #SearchAlgorithm
+ [[https://ai.googleblog.com/2018/10/introducing-adanet-fast-and-flexible.html][Introducing AdaNet: Fast and Flexible AutoML with Learning Guarantees]] ~ C. Weill #Ensemble #AutoML #ReinforcementLearning
+ [[https://www.oreilly.com/radar/drivetrain-approach-data-products/][Designing great data products]] ~ J. Howard #DataProducts #Pipeline
+ [[https://ai.googleblog.com/2018/11/open-sourcing-bert-state-of-art-pre.html][Open Sourcing BERT: State-of-the-Art Pre-training for Natural Language Processing]] ~ J. Devlin #NaturalLanguageProcessing #BERT #PreTraining #SemiSupervisedLearning
+ [[https://arxiv.org/pdf/1505.04597.pdf][U-Net: Convolutional Networks for Biomedical Image Segmentation]] ~ O. Ronneberger #SemanticSegmentation
+ [[https://windowsontheory.org/2019/12/05/deep-double-descent/][Deep Double Descent]] ~ OpenAI #Methods #DeepNeuralNetworks
+ [[https://arxiv.org/pdf/1707.08721.pdf][Exploiting Web Images for Weakly Supervised Object Detection]] ~ Q. Tao #ObjectDetection #WeakSupervisedLearning #CurriculumLearning
+ [[https://www.biorxiv.org/content/10.1101/541862v1.full.pdf][Deep learning reveals cancer metastasis and therapeutic antibody targeting in whole body]] ~ C. Pan #MedicalImaging 
+ [[https://medium.com/mlreview/machine-learning-on-graphs-neurips-2019-875eecd41069][Machine Learning on Graphs @ NeurIPS 2019]] ~ M. Galkin #Graphs #GraphConvolutionalNetworks #Embeddings
+ [[https://github.com/ageron/handson-ml2][Machine Learning Notebooks]] ~ A. Géron #MachineLearning #JupyterNotebooks #Resources
+ [[https://academic.oup.com/bioinformatics/advance-article/doi/10.1093/bioinformatics/btz699/5564115][Protein–protein interaction site prediction through combining local and global features with deep neural networks]] ~ M. Zeng #Proteins #Chemistry 
+ [[https://www.nature.com/articles/s41598-019-46369-4][Predicting Protein-Protein Interactions from Matrix-Based Protein Sequence Using Convolution Neural Network and Feature-Selective Rotation Forest]] ~ L. Wang #ConvolutionalNeuralNetworks #Proteins #Chemistry
+ [[https://github.com/jupyter/jupyter/wiki/A-gallery-of-interesting-Jupyter-Notebooks][A gallery of interesting Jupyter Notebooks]] ~ J. C. Agar #JupyterNotebooks #Resources
+ [[https://arxiv.org/abs/1907.09595v3][MixConv: Mixed Depthwise Convolutional Kernels]] ~ M. Tan #Mobile #ImageClassification #NeuralArchitectureSearch
+ [[https://towardsdatascience.com/advances-in-few-shot-learning-a-guided-tour-36bc10a68b77?][Advances in few-shot learning: a guided tour]] ~ O. Knagg #FewShotLearning #MatchingNetworks
+ [[https://towardsdatascience.com/advances-in-few-shot-learning-reproducing-results-in-pytorch-aba70dee541d][Advances in few-shot learning: reproducing results in PyTorch]] ~ O. Knagg #FewShotLearning #MatchingNetworks
+ [[https://drive.google.com/file/d/1VIeV7l9x-KXdT_UdZB54GQxhGHRRQ79T/view][Selective Brain Damage: Measuring the Disparate Impact of Model Pruning]] ~ S. Hooker #Pruning #Robustness
+ [[https://arxiv.org/pdf/1905.02249.pdf][MixMatch: A Holistic Approach to Semi-Supervised Learning]] ~ D. Berthelot #SemiSupervisedLearning 
+ [[https://arxiv.org/pdf/1912.02636.pdf][Exploration of Neural Machine Translation inAutoformalization of Mathematics in Mizar]] ~ J. Urban #NaturalLanguageProcessing #ITPs  
+ [[https://www.forbes.com/sites/robtoews/2019/11/17/to-understand-the-future-of-ai-study-its-past/#32f2ad3721b3][To Understand The Future of AI, Study Its Past]] ~ R. Toews #ArtificialIntelligence #History #Connectionist #Symbolism
+ [[https://machinelearningmastery.com/super-learner-ensemble-in-python/][How to Develop Super Learner Ensembles in Python]] ~ J. Brownlee #Ensemble #MetaLearner #SuperLearner
+ [[https://arxiv.org/abs/1811.04017][A generic framework for privacy preserving deep learning]] ~ T. Ryffel #Privacy #FederatedLearning #DifferentialPrivacy
+ [[https://slideslive.com/38921496/human-behavior-modeling-with-machine-learning-opportunities-and-challenges][Human Behavior Modeling with Machine Learning: Opportunities and Challenges]] ~ N. Oliver #HumanBehaviour
+ [[https://arxiv.org/pdf/1912.04958.pdf][Analyzing and Improving the Image Quality of StyleGAN]] ~ T. Karras #GANs #StyleGAN 
+ [[https://www.youtube.com/watch?v=9iol3Lk6kyU][A Bluffer's Guide to Dimension Reduction]] ~ L. McInnes #DimensionalityReduction #Video #Overview
+ [[https://arxiv.org/pdf/1806.10758.pdf][A Benchmark for Interpretability Methods in DeepNeural Networks]] ~ S. Hooker #Interpretability #FeatureImportance
+ [[https://blog.openmined.org/upgrade-to-federated-learning-in-10-lines/][Deep Learning -> Federated Learning in 10 Lines of PyTorch + PySyft]] ~ T. Ryffel #FederatedLearning #Privacy #PySyft
+ [[https://arkhn.com/en/federated/][Federated Learning]] ~ Arkhn #FederatedLearning #Privacy
+ [[https://arxiv.org/pdf/1908.07836.pdf][PubLayNet: largest dataset ever for documentlayout analysis]] ~ X. Zhong #DocumentAnalysis #Athento #Dataset #Tables
+ [[https://arxiv.org/abs/1606.00915][DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs]] ~ L-C. Chen #SemanticSegmentation 
+ [[https://medium.com/@fedor.kitashov/ai-based-photo-restoration-6e41469ce0d7][AI-Based Photo Restoration]] ~ F. Kitashov #GANs #U-net #Colorisation #Inpainting
+ [[https://www.youtube.com/watch?v=jiLPUkpH6Kg&list=PLoh75bAP4Qoh_DKJGrWudy9GNTNEzyXvG&index=3&t=0s][Future of individualized medicine]] ~ J. Howard #Medicine #ArtificialIntelligence
+ [[https://colab.research.google.com/drive/1UCJt8EYjlzCs1H1d1X0iDGYJsHKwu-NO][TensorFlow 2.0 + Keras Overview for Deep Learning Researchers]] ~ F. Chollet #Keras #Tensorflow
+ [[https://www.biorxiv.org/content/biorxiv/early/2019/04/11/606202.full.pdf][Deciphering interaction fingerprints from protein molecular surfaces]] ~ P. Gainza #Chemistry #Molecules
+ [[https://emtiyaz.github.io/papers/learning_from_bayes.pdf][Learning-Algorithms from Bayesian Principles]] ~ M. Emtiyaz #LearningAlgorithms
+ [[https://arxiv.org/pdf/1905.09272v2.pdf][Data-efficient image recognition with contrastive predictive coding]] ~ O. J. Hénaff  #RepresentationLearning #ImageClassification #SemiSupervisedLearning 
+ [[https://arxiv.org/pdf/1706.03762.pdf][Attention is all you need]] ~ A. Vaswani #MachineTranslation #Attention #Transformers #NaturalLanguageProcessing
+ [[http://eyeriss.mit.edu/2019_neurips_tutorial.pdf][Efficient Processing of Deep Neural Networks:from Algorithms to Hardware Architectures]] ~ V. Sze #Efficiency #Consumption #Hardware
+ [[https://autogluon.mxnet.io/][AutoGluon: AutoML Toolkit for Deep Learning]] ~ Gluon #AutoML #ImageClassification #ObjectDetection
+ [[https://medium.com/@NeurIPSConf/what-we-learned-from-neurips-2019-data-111ab996462c][What we learned from NeurIPS 2019 data]] ~ NeurIPS
+ [[http://openaccess.thecvf.com/content_cvpr_2018/papers/Murez_Image_to_Image_CVPR_2018_paper.pdf][Image to Image Translation for Domain Adaptation]] ~ Z. Murez #DomainAdaptation #EncoderDecoder #DomainShift
+ [[https://towardsdatascience.com/10-lessons-i-learned-training-generative-adversarial-networks-gans-for-a-year-c9071159628][10 Lessons I Learned Training GANs for one Year]] ~ M. Pasini #GANs #Tricks
+ [[https://jupyterhub.readthedocs.io/en/latest/getting-started/institutional-faq.html][Institutional JupyterHub]] ~ JupyterHub #JupyterNotebooks
+ [[https://medium.com/sciforce/robust-image-classification-with-a-small-data-set-be4de9897495][Robust image classification with a small data set]] ~ Sciforce #ImageClassification #TransferLearning #DomainAdapatation #FewShotLearning
+ [[https://arxiv.org/pdf/1909.01958.pdf][From ‘F’ to ‘A’ on the N.Y. Regents Science Exams:An Overview of the Aristo Project]] ~ P. Clark #NaturalLanguageProcessing #QuestionAnswering #Aristo
+ [[https://www.microsiervos.com/archivo/ia/inteligencia-artificial-notas-sobresalientes-examenes-ciencias.html][La inteligencia artificial capaz de puntuar con notas sobresalientes en los exámenes de ciencias]] ~ Microsiervos #ArtificialIntelligence #Mathematics
+ [[https://arxiv.org/abs/1911.11763][SuperGlue: Learning Feature Matching with Graph Neural Networks]] ~ P-E. Sarlin # GraphNeuralNetworks #PoseEstimation #Matching #Homography
+ [[https://ai.googleblog.com/2017/04/predicting-properties-of-molecules-with.html][Predicting Properties of Molecules with Machine Learning]] ~ G. Dahl #GraphNeuralNetworks #Chemistry
+ [[https://ai.googleblog.com/2019/10/learning-to-smell-using-deep-learning.html][Learning to Smell: Using Deep Learning to Predict the Olfactory Properties of Molecules]] ~ A. Wiltschko #Smell #DeepNeuralNetworks #GraphNeuralNetworks #Embeddings #Chemistry
+ [[https://docs.google.com/presentation/d/e/2PACX-1vTm9axI6uc6jW9-ttgQrgSNddAkIrFcQnfQ3jspI89iwcDS1MpmmKWDT_zdySrdMgLqQ6d5QvOoZUmy/pub?start=false&loop=false&delayms=30000#slide=id.p][Open Science Forum: Principles and practice]] ~ G. Way #OpenScience
+ [[https://www.pyimagesearch.com/2019/12/02/opencv-vehicle-detection-tracking-and-speed-estimation/][OpenCV Vehicle Detection, Tracking, and Speed Estimation]] ~ A. Rosebrock #PyimageSearch #VehicleDetection #OpenCV #RaspberryPi
+ [[https://www.pyimagesearch.com/2019/11/25/human-activity-recognition-with-opencv-and-deep-learning/][Human Activity Recognition with OpenCV and Deep Learning]] ~ A. Rosebrock #PyimageSearch #HumanActivityRecognition #VideoRecognition #KineticsDataset #3DConvs
+ [[https://www.pyimagesearch.com/2019/10/28/3-ways-to-create-a-keras-model-with-tensorflow-2-0-sequential-functional-and-model-subclassing/][3 ways to create a Keras model with TensorFlow 2.0 (Sequential, Functional, and Model Subclassing)]] ~ A. Rosebrock #PyimageSearch #Keras #Tensorflow
+ [[https://lisp-journey.gitlab.io/pythonvslisp/][Python VS Common Lisp, workflow and ecosystem]] ~ H. Beg #ProgrammingLanguages #Lisp #Python
+ [[https://medium.com/dataseries/interactive-convolutional-neural-network-65bc19d8d698][Interactive Convolutional Neural Network]] ~ V. Alto #Streamlit #ConvolutionalNeuralNetworks #Interactive #Visualization
+ [[https://arxiv.org/pdf/1905.11946.pdf][EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks]] ~ M. Tan #ConvolutionalNeuralNetworks #ImageClassification #EfficientNet #NeuralArchitectureSearch #ModelScaling
+ [[https://arxiv.org/abs/1912.01412][Deep Learning for Symbolic Mathematics]] ~ G. Lample #DeepLearning #ComputerAlgebraSystems 
+ [[https://arxiv.org/pdf/1911.13299.pdf][What’s Hidden in a Randomly Weighted Neural Network?]] ~ V. Ramanujan #UntrainedNetworks #Subnetworks #LotteryTicket
+ [[https://arxiv.org/abs/1903.03425][The Ethics of AI Ethics -- An Evaluation of Guidelines]] ~ T. Hagendorff #Ethics #Guidelines
+ [[https://arxiv.org/pdf/1703.06870.pdf][Mask R-CNN]] ~ K. He #ObjectDetection #SemanticSegmentation #MultiTaskLearning
+ [[https://arxiv.org/abs/1911.04252][Self-training with Noisy Student improves ImageNet classification]] ~ Q. Xie #SelfTraining #ImageClassification #SemiSupervisedLearning #EfficientNet
+ [[https://medium.com/just-ai/nimbus-cloud-segmentation-using-deep-learning-for-agriculture-5f1320b5c8aa][Nimbus — Cloud Segmentation using Deep Learning for Agriculture.]] ~ G. Rahman #Copernicus #Agriculture #IDERioja #SemanticSegmentation
+ [[https://logtalk.org/2019/11/13/many-worlds-design-pattern.html][The "many worlds" design pattern]] ~ P. Moura #DesignPatterns #Programming #Prolog
+ [[http://deliprao.com/archives/342][The Doers and The Clarion Callers]] ~ Delip #ArtificialIntelligence #Connectionism #Symbolism
+ [[https://arxiv.org/pdf/1901.09005.pdf][Revisiting Self-Supervised Visual Representation Learning]] ~ A. Kolesnikov #SelfSupervisedLearning #RepresentationLearning
+ [[https://arxiv.org/pdf/1708.07860.pdf][Multi-task Self-Supervised Visual Learning]] ~ C. Doersch #SelfSupervisedLearning #MultiTaskLearning #RepresentationLearning
+ [[https://www.fast.ai/2019/12/02/nbdev/][nbdev: use Jupyter Notebooks for everything]] ~ J. Howard #JupyterNotebooks #ProgrammingEnvironment #Python
+ [[https://arxiv.org/abs/1606.03498][Improved Techniques for Training GANs]] ~ T. Salimans #GANs #TrainingMethods #SemiSupervisedLearning 
+ [[https://deepai.org/publication/artificial-intelligence-for-diagnosis-of-skin-cancer-challenges-and-opportunities][Artificial Intelligence for Diagnosis of Skin Cancer: Challenges and Opportunities]] ~ M. Goyal #MedicalImaging #Review #Datasets
+ [[https://towardsdatascience.com/bayesian-deep-learning-with-fastai-how-not-to-be-uncertain-about-your-uncertainty-6a99d1aa686e][Bayesian deep learning with Fastai : how not to be uncertain about your uncertainty]] ~ D. Huynh #BayesianNeuralNetworks #FastAI
+ [[https://towardsdatascience.com/how-i-created-over-100-000-labeled-lego-training-images-ec74191bb4ef][How I created over 100,000 labeled LEGO training images]] ~ D. West #Annotation 
+ [[https://codesync.global/media/revolution-in-computing-education-at-school-opportunity-and-challenge-cmldn19/][The revolution in computing education at school: opportunity and challenge]] ~ S. Peyton Jones #ComputerScience #Education
+ [[https://www.tweag.io/posts/2019-11-28-pcf-makam-spec][How to make your papers run: executable formal semantics for your language]] ~ T. Freund #FormalMethods #Makam #OperationalSemantics
+ [[https://fairmlbook.org/index.html][Fairness and machine learning]] ~ S. Barocas #Ethics #Fairness
+ [[https://blog.dropbox.com/topics/work-culture/-the-mind-at-work--guido-van-rossum-on-how-python-makes-thinking][The Mind at Work: Guido van Rossum on how Python makes thinking in code easier]] ~ A. Wing Kosner #Programming #Python
+ [[https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3994246/pdf/1758-2946-6-10.pdf][Cross-validation pitfalls when selecting andassessing regression and classification models]] ~ D. Krstajic #CrossValidation #MachineLearning #ProperEvaluation

** Noviembre 2019
#+html: <p align="center"><img src="wordClouds/noviembre2019.png" /></p>

+ [[https://diginomica.com/ai-curve-fitting-not-intelligence][AI today and tomorrow is mostly about curve fitting, not intelligence]] ~ K. Marko #ArtificialIntelligence #ArtificialGeneralIntelligence
+ [[https://arxiv.org/abs/1511.06434][Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks]] ~ A. Radford #GANs
+ [[https://arxiv.org/pdf/1406.2661.pdf][Generative Adversarial Nets]] ~ I. Goodfellow. #GANs
+ [[https://arxiv.org/pdf/1902.06162.pdf][Self-supervised Visual Feature Learning withDeep Neural Networks: A Survey]] ~ L. Jing #SelfSupervisedLearning #TransferLearning 
+ [[https://arxiv.org/pdf/1911.10317.pdf][PlantDoc: A Dataset for Visual Plant Disease Detection]] ~ D. Singh #Datasets #ObjectDetection
+ [[http://openaccess.thecvf.com/content_CVPR_2019/papers/Lee_Multi-Task_Self-Supervised_Object_Detection_via_Recycling_of_Bounding_Box_Annotations_CVPR_2019_paper.pdf][Multi-task Self-supervised Object Detectionvia Recycling of Bounding Box Annotations]] ~ W. Lee #SelfSupervisedLearning #ObjectDetection #MultiClassLearning
+ [[https://arxiv.org/abs/1804.09170][Realistic Evaluation of Deep Semi-Supervised Learning Algorithms]] ~ A. Oliver #SemiSupervisedLearning #Evaluation #ImageClassification
+ [[https://arxiv.org/pdf/1905.03670.pdf][S4L: Self-Supervised Semi-Supervised Learning]] ~ X. Zhai #SelfSupervisedLearning #SemiSupervisedLearning
+ [[https://arxiv.org/pdf/1911.07309v1.pdf][Coverage Testing of Deep Learning Models using Dataset Characterization]] ~ S. Mani #Testing #DeepLearning
+ [[https://smerity.com/articles/2017/baselines_need_love.html][Backing off towards simplicity - why baselines need more love]] ~ S. Merity #Baselines #DeepLearning
+ [[https://smerity.com/articles/2018/limited_compute.html][The compute and data moats are dead]] ~ S. Merity #BigData #LimitedComputation 
+ [[https://arxiv.org/abs/1911.11423][Single Headed Attention RNN: Stop Thinking With Your Head]] ~ S. Merity #NaturalLanguageProcessing #LanguageModelling
+ [[https://arxiv.org/abs/1610.05755][Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data]] ~ N. Papernot #DifferentialPrivacy #PATE #Ensemble #SemiSupervisedLearning
+ [[https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8689016][Enhance PATE on Complex Tasks With Knowledge Transferred From Non-Private Data]] ~ L. Wang #DifferentialPrivacy #Ensemble #ImageClassification
+ [[https://arxiv.org/pdf/1802.08908.pdf][Scalable Private Learning with PATE]] ~ N. Papernot #DifferentialPrivacy #Ensemble
+ [[https://desfontain.es/privacy/differential-privacy-awesomeness.html][Why differential privacy is awesome]] ~ D. Desfontaines #DifferentialPrivacy #Security #Series
+ [[https://www.papernot.fr/teaching/f19/ECE1784H_7.pdf][Differential Privacy]] ~ N. Papernot #DifferentialPrivacy #Security
+ [[https://arxiv.org/abs/1911.08855][RefineDetLite: A Lightweight One-stage Object Detection Framework for CPU-only Devices]] ~ C. Chen #ObjectDetection #Mobile #SmallNetworks
+ [[https://arxiv.org/pdf/1811.05588.pdf][YOLO-LITE: A Real-Time Object DetectionAlgorithm Optimized for Non-GPU Computers]] ~ R. Huang. #ObjectDetection #Mobile #SmallNetworks
+ [[https://machinelearningmastery.com/types-of-learning-in-machine-learning/][14 Different Types of Learning in Machine Learning]] ~ J. Brownlee #Classification #SemiSupervisedLearning #SelfSupervisedLearning
+ [[https://pair-code.github.io/understanding-umap/][Understanding UMAP]] ~ A. Coenen #DimensionalityReduction 
+ [[https://arxiv.org/pdf/1807.11626.pdf][MnasNet: Platform-Aware Neural Architecture Search for Mobile]] ~ M. Tan #AutoML #NeuralArchitectureSearch #Mobile
+ [[https://medium.com/@santiagof/auto-is-the-new-black-google-automl-microsoft-automated-ml-autokeras-and-auto-sklearn-80d1d3c3005c][Auto is the new black — Google AutoML, Microsoft Automated ML, AutoKeras and auto-sklearn]] ~ F. Santiago #AutoML
+ [[https://medium.com/@santiagof/model-interpretability-making-your-model-confess-shapley-values-5fb95a10a624][Model interpretability — Making your model confess: Shapley values]] ~ F. Santiago #Interpretability #Fairness #Privacy #Robustness #Causality #Trust
+ [[https://towardsdatascience.com/deep-dive-into-the-computer-vision-world-part-3-abd7fd2c64ef][YOLO, SSD, FPN and RetinaNet, more unified ones]] ~ J. Jeong #ObjectDetection #Architectures 
+ [[https://arxiv.org/abs/1910.14667][Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors]] ~ Z. Wu #AdversialAttacks #ObjectDetectors
+ [[https://www.frontiersin.org/articles/10.3389/fcomp.2019.00010/full?utm_source=F-NTF&utm_medium=EMLX&utm_campaign=PRD_FEOPS_20170000_ARTICLE][Generative Adversarial Networks for Augmenting Training Data of Microscopic Cell Images]] ~ P. Baniukiewicz #DataAugmentation #Microscopy #GANs
+ [[https://medium.com/@bu64dcjrytwitb8/on-recent-research-auditing-commercial-facial-analysis-technology-19148bda1832][On Recent Research Auditing Commercial Facial Analysis Technology]] ~ Concerned Researchers #Ethics #FaceRecognition 
+ [[http://ai.stanford.edu/blog/weak-supervision/][Weak Supervision: A New Programming Paradigm for Machine Learning]] ~ A. Ratner #WeakSupervision
+ [[http://c-faq.com/decl/spiral.anderson.html][The Clockwise/Spiral Rule]] ~ D. Anderson #C++
+ [[https://arxiv.org/abs/1911.09070][EfficientDet: Scalable and Efficient Object Detection]] ~ M. Tan #ObjectDetection
+ [[http://matryoshka.gforge.inria.fr/pubs/deep_learning_paper.pdf][A formal proofof the expressiveness of deep learning]] ~ A. Bentkamp #Isabelle/HOL #MachineLearningProofs
+ [[http://ace.cs.ohio.edu/~gstewart/papers/aaai19-bagnall.pdf][Certifying the True Error: Machine Learning in Coq with Verified Generalization Guarantees]] ~ A. Bagnall #Coq #MachineLearningProofs #Tensorflow
+ [[https://arxiv.org/abs/1911.00385][A Formal Proof of PAC Learnability for Decision Stumps]] ~ J. Tassarotti. #TheoremProving #AdrianLanguage 
+ [[https://medium.com/@jdchipox/how-to-interact-with-jupyter-33a98686f24e][How to create buttons in Jupyter]] ~ D. Penilla #JupyterNotebooks #Interaction
+ [[http://blog.ibanyez.info/blogs/coding/20190410-run-a-google-colab-notebook-to-train-yolov3-using-darknet-in/][How to train YOLOv3 using Darknet on Colab]] ~ D. Ibáñez #Colab #ObjectDetection #YOLO
+ [[https://medium.com/analytics-vidhya/training-an-object-detection-model-with-tensorflow-api-using-google-colab-4f9a688d5e8b][Training an Object Detection Model with TensorFlow API using Google COLAB]] ~ N. O. Solomon #ObjectDetection #Colab
+  [[https://icml.cc/Conferences/2017/Schedule?showParentSession=1116][Semisupervised and curriculum learning conference]] #CurriculumLearning #SupervisedLearning #Conference
+ [[https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7465792][Multi-Modal Curriculum Learning forSemi-Supervised Image Classification]] ~ C. Gong #SemiSupervisedLearning #CurriculumLearning #ImageClassification
+ [[https://ronan.collobert.com/pub/matos/2009_curriculum_icml.pdf][Curriculum Learning]] ~ Y. Bengio #CurriculumLearning 
+ [[https://weightpruningdamage.github.io/][Selective Brain Damage: Measuring the Disparate Impact of Model Compression]] ~ S. Hooker #Prunning #NeuralCompression
+ [[https://www.technologyreview.com/s/614742/machine-learning-has-revealed-exactly-how-much-of-a-shakespeare-play-was-written-by-someone/][Machine learning has revealed exactly how much of a Shakespeare play was written by someone else]] ~  P. Plecháč #NaturalLanguageProcessing 
+ [[https://www.nature.com/articles/s41467-019-12552-4][The Eighty Five Percent Rule for optimal learning]] ~ R. C. Wilson. #CurriculumLearning #Learning #LearningRate
+ [[https://www.uni-bonn.de/news/196-2019][Artificial intelligence in the fight against river blindness]] ~ Klarmann-Schulz #MedicalImages #ArtificialIntelligence
+ [[https://reader.elsevier.com/reader/sd/pii/S092523121930459X?token=018CD1D1335019467EE0F3ACAD5DD2811A5F777EE89CD49B37C063D9D0CB55920EEB7BDE2F7A49D4FD764CAA82A85CB9][Hybrid methodology based on Bayesian optimization and GA-PARSIMONY to search for parsimony models by combining hyperparameter optimization and feature selection]] ~ F. J. Martinez-de-Pison #GeneticAlgorithms #HyperparameterTuning # FeatureSelection
+ [[https://reader.elsevier.com/reader/sd/pii/S0925231217312171?token=8393125D6089846543BD22B53D74F1DAF0D3692CA6C573D49717ABD84F550FC17EF6C05C186796FDEBAF12784C34EC61][Evaluation of a novel GA-based methodology for model structure selection: The GA-PARSIMONY]] ~ F. J. Martinez-de-Pison #GeneticAlgorithms #HyperparameterTuning # FeatureSelection
+ [[https://machinelearningmastery.com/computer-vision-books/][8 Books for Getting Started With Computer Vision]] ~ J. Brownlee #ComputerVision #Books
+ [[https://arxiv.org/pdf/1503.03832.pdf][FaceNet: A Unified Embedding for Face Recognition and Clustering]] ~ F. Schroff #FaceRecognition #TripletLoss 
+ [[https://arxiv.org/pdf/1702.08734.pdf][Billion-scale similarity search with GPUs]] ~ J. Johnson #SimilaritySearch #GPUs
+ [[https://www.cs.cmu.edu/~rsalakhu/papers/oneshot1.pdf][Siamese Neural Networks for One-shot Image Recognition]] ~ G. Koch #OneShotLearning #SiameseNetworks 
+ [[https://towardsdatascience.com/image-similarity-using-triplet-loss-3744c0f67973][Image similarity using Triplet Loss]] ~ S. Das #TripletLoss
+ [[https://towardsdatascience.com/u-nets-with-resnet-encoders-and-cross-connections-d8ba94125a2c][U-Nets with ResNet Encoders and cross connections]] ~ C. Thomas #FastAI #UNet 
+ [[https://arxiv.org/pdf/1711.09784.pdf][Distilling a Neural Network into a soft decision tree]] ~ N. Frosst. #Explanability #Distillation #SemiSupervisedLearning
+ [[https://elpais.com/elpais/2019/11/06/ciencia/1573042148_224789.html][Qué es la teoría de categorías y cómo se ha convertido en tendencia]] ~ J. Baez #TeoriaCategorias #Logica 
+ [[https://www.biorxiv.org/content/10.1101/799270v1][DeepImageJ: A user-friendly plugin to run deep learning models in ImageJ]] ~ E. Gómez-de-Mariscal #ImageJ #DeepLearning 
+ [[https://lilianweng.github.io/lil-log/2018/06/24/attention-attention.html][Attention? Attention!]] ~ L. Weng #Attention #NLP
+ [[https://lilianweng.github.io/lil-log/2019/11/10/self-supervised-learning.html][Self-Supervised Representation Learning]] ~ L. Weng #SemiSupervised #Survey #PretextTasks
+ [[https://arxiv.org/abs/1906.11172][Learning Data Augmentation Strategies for Object Detection]] ~ B. Zoph. #DataAugmentation #ObjectDetection #AutoML

** Octubre 2019
#+html: <p align="center"><img src="wordClouds/octubre2019.png" /></p>

+ [[https://arxiv.org/pdf/1910.10685.pdf][Machine Learning for Scent: Learning Generalizable Perceptual Representations of Small Molecules]] ~ B. Sanchez-Lengeling #GraphNeuralNetworks #Molecules #Scent
+ [[https://arxiv.org/pdf/1901.00596.pdf][A Comprehensive Survey on Graph Neural Networks]] ~ Z. Wu. #Survey #GraphNeuralNetworks
+ [[https://mml-book.github.io/book/mml-book.pdf][Mathematics for Machine Learning]] ~ M. P. Deisenroth. #Book #MachineLearning #Mathematics
+ [[https://cacm.acm.org/magazines/2019/11/240390-deepxplore/fulltext][DeepXplore: Automated Whitebox Testing of Deep Learning Systems]] ~ K. Pei #DeepLearning #Interpretability #Reliability
+ [[https://www.biorxiv.org/content/10.1101/265231v1][End-so-end differentiable learning of protein structure]] ~ M. AlQuraishi #DeepLearning #Proteins
+ [[https://www.biorxiv.org/content/10.1101/465955v4][Distance-based Protein Folding Powered by Deep Learning]] ~ J. Xu #DeepLearning #Proteins
+ [[https://lukeoakdenrayner.wordpress.com/2019/10/14/improving-medical-ai-safety-by-addressing-hidden-stratification/][Improving Medical AI Safety by Addressing Hidden Stratification]] ~ Luke Oakden-Rayner #AISafety 
+ [[https://www.pyimagesearch.com/2019/10/21/keras-vs-tf-keras-whats-the-difference-in-tensorflow-2-0/][Keras vs. tf.keras: What’s the difference in TensorFlow 2.0?]] ~ A. Rosebrock #PyimageSearch #Keras #TensorflowV2
+ [[https://ai.facebook.com/blog/billion-scale-semi-supervised-learning/][Billion-scale semi-supervised learning for state-of-the-art image and video classification]] ~ I. Zeki Yalniz. #SemiSupervisedLearning #WeakSupervisedLearning
+ [[https://storage.googleapis.com/pub-tools-public-publication-data/pdf/43146.pdf][Machine Learning: The High-Interest Credit Card of Technical Debt]] ~ D. Sculley. #MachineLearning #TechnicalRisks
+ [[https://www.pyimagesearch.com/2019/10/14/why-is-my-validation-loss-lower-than-my-training-loss/][Why is my validation loss lower than my training loss?]] ~ A. Rosebrock #Pyimagesearch #ValidationLoss
+ [[https://arxiv.org/pdf/1906.07155.pdf][MMDetection: Open MMLab Detection Toolbox and Benchmark]] ~ K. Chen. #ObjectDetection #Library
+ [[https://openlibra.com][OpenLibra]] #Libros #Gratuitos
+ [[https://arxiv.org/pdf/1907.11093v1.pdf][SlimYOLOv3:Narrower, Faster and Better for Real-Time UAV Applications]] ~ P. Zhang. #ObjectDetection #Yolo #ModelPrunning
+ [[https://levelup.gitconnected.com/5-important-changes-coming-with-tensorflow-2-0-e6bb172c5fdf][5 Important Changes Coming with TensorFlow 2.0]] ~ G. Seif #Tensorflow #DeepLearning
+ [[https://arxiv.org/pdf/1905.00546.pdf][Billion-scale semi-supervised learning for image classification]] ~ I. Zeki Yalniz #SemiSupervisedLearning #ImageClassification
+ [[https://arxiv.org/pdf/1908.11415v1.pdf][Translating Mathematical Formula Images to LaTeX Sequences Using Deep Neural Networks with Sequence-level Training]] ~ Z. Wang. #EncoderDecoder #LSTM #CNNs #OCR 
+ [[https://arxiv.org/abs/1905.13549][Learning Robust Global Representations by Penalizing Local Predictive Power]] ~ H. Wang. #ImageClassification #Robustness #GlobalPatterns
+ [[https://www.pyimagesearch.com/2019/09/30/rectified-adam-radam-optimizer-with-keras/][Rectified Adam (RAdam) optimizer with Keras]] ~ A. Rosebrock #PyimageSearch #Optimization

** Septiembre 2019
#+html: <p align="center"><img src="wordClouds/septiembre2019.png" /></p>

+ [[https://blog.insightdatascience.com/automl-for-data-augmentation-e87cf692c366][AutoML for Data Augmentation]]. ~
  Barış Özmen. #DeepLearning #AutoML #ImageAugmentation
+ [[http://openaccess.thecvf.com/content_ECCV_2018/papers/Yongqiang_Zhang_SOD-MTGAN_Small_Object_ECCV_2018_paper.pdf][SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network]] ~ Yancheng Bai. #GANs #SuperResolution #ObjectDetection
+ [[https://deepai.org/publication/topology-preserving-augmentation-for-cnn-based-segmentation-of-congenital-heart-defects-from-3d-paediatric-cmr][Topology-preserving augmentation for CNN-based segmentation of congenital heart defects from 3D paediatric CMR]] ~ Nick Byrne. #MedicalImages #SemanticSegmentation #ImageAugmentation #Topology
+ [[https://www.nature.com/articles/d41586-019-02514-7][Halt the use of facial-recognition technology until it is regulated]] ~ Kate Crawford. #FaceRecognition #Ethics
+ [[https://www.pyimagesearch.com/2019/08/26/building-an-image-hashing-search-engine-with-vp-trees-and-opencv/][Building an Image Hashing Search Engine with VP-Trees and OpenCV]] ~ Adrian Rosebrock. #ImageProcessing #SearchEngine #OpenCV #VPTree #PyImageSearch
+ [[https://arxiv.org/pdf/1907.11457.pdf][Two-hidden-layer feedforward networks are universal approximators: a constructive approach]] ~ Rocío González-Díaz #NeuralNetworks  #SimplicialComplexes #UniversalTheorem
+ [[https://www.kaggle.com/mbkinaci/fruit-images-for-object-detection][Fruit Images for Object Detection]] ~ Muhammed Buyukkinaci. #Datasets #ObjectDetection
+ [[https://arxiv.org/pdf/1712.04440.pdf][Data Distillation: Towards Omni-Supervised Learning]] ~ Ilija Radosavovic. #SemiSupervisedLearning #Ensembles #DataDistillation #OmniSupervisedLearning
+ [[https://link.springer.com/content/pdf/10.1007%2F978-3-030-00928-1_65.pdf][Omni-Supervised Learning: Scaling Upto Large Unlabelled Medical Datasets]] ~ Ruobing Huang. #MedicalImages #OmniSupervisedLearning
+ [[https://towardsdatascience.com/facebook-believes-in-omni-supervised-learning-78f37253f4f4][Facebook Believes in Omni-Supervised Learning]] ~ Jesus Rodriguez. #OmniSupervisedLearning #DeepLearning
+ [[http://openaccess.thecvf.com/content_CVPR_2019/papers/Iscen_Label_Propagation_for_Deep_Semi-Supervised_Learning_CVPR_2019_paper.pdf][Label Propagation for Deep Semi-supervised Learning]] ~ Ahmet Iscen. #SemiSupervisedLearning #ImageClassification #TransductiveLearning
+ [[https://medium.com/bethgelab/neural-networks-seem-to-follow-a-puzzlingly-simple-strategy-to-classify-images-f4229317261f][Neural Networks seem to follow a puzzlingly simple strategy to classify images]] ~ W. Brendel. #ImageClassification #DeepLearning #BagOfFeatures #Interpretability
+ [[https://arxiv.org/pdf/1907.07484.pdf][Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming]] ~ C. Michaelis. #ObjectDetection #AdversialAttacks #Robustness. [[https://github.com/bethgelab/mmdetection][Associated benchmark]].
+ [[https://towardsdatascience.com/when-conventional-wisdom-fails-revisiting-data-augmentation-for-self-driving-cars-4831998c5509][When Conventional Wisdom Fails: Revisiting Data Augmentation for Self-Driving Cars]] ~ M. Cooper. #ImageAugmentation #AblationStudy #ObjectDetection #DataConsistency
+ [[https://www.thelancet.com/journals/landig/article/PIIS2589-7500(19)30108-6/fulltext][Automated deep learning design for medical image classification by health-care professionals with no coding experience: a feasibility study]] ~ L. Faes. #AutoML #ImageClassification #MedicalImages
+ [[https://martinfowler.com/articles/cd4ml.html][https://martinfowler.com/articles/cd4ml.html]] ~ D. Sato. #ContinuousDelivery #MachineLearning
+ [[https://rsomani95.github.io/ai-film-1.html][AI for filmmaking]] ~ R. Somali. #ImageClassification #FastAI #Resnet
+ [[https://medium.com/starschema-blog/transfer-learning-the-dos-and-donts-165729d66625][Transfer learning: the dos and don’ts]] ~ C. Von Csefalvay. #TransferLearning #DeepLearning #Recipes
+ [[https://arxiv.org/pdf/1905.08942v2.pdf][The Machine Learning Bazaar: Harnessing the ML Ecosystem for Effective System Development]] ~ M. J. Smith. #AutoML #PapersWithCode 
+ [[https://papers.nips.cc/paper/5656-hidden-technical-debt-in-machine-learning-systems.pdf][Hidden Technical Debt in Machine Learning Systems]] ~ D. Ebner. #MachineLearning #Development #Risks
+ [[https://worldmodels.github.io/][World Models: Can agents learn inside of their own dreams]] ~ D. Ha. #ReinforcementLearning #GANs
+ [[https://arxiv.org/pdf/1803.07728.pdf][Unsupervised Representation Learning by Predicting Image Rotations]] ~ S. Gidaris. #ImageClassification #SelfSupervisedLearning #DataAugmentation
+ [[https://medium.com/in-the-pocket-insights/data-labeling-made-simple-and-cheap-3f6ecb54697d][Data labeling made simple (and cheap)]] ~ F. Degroote. #ObjectDetection #AutoLabelling #[[https://github.com/marcotcr/lime][Lime]]
+ [[https://arxiv.org/pdf/1602.04938.pdf]["Why Should I Trust You?" Explaining the Predictions of Any Classifier]] ~ M. T. Ribeiro. #Interpretability #[[https://github.com/marcotcr/lime][Lime]] #Explainability
+ [[https://medium.com/health-ai/google-deepmind-might-have-just-solved-the-black-box-problem-in-medical-ai-3ed8bc21f636][Google DeepMind might have just solved the "Black Box" problem in medical AI]] ~ S. Ruyu Qi. #Interpretability #Healthcare #Unet
+ [[https://imo-grand-challenge.github.io/][IMO Grand Challenge]] ~ D. Selsam #Lean #AutomatedTheoremProving #MathematicalOlympiad
+ [[https://www.hillelwayne.com/post/theorem-prover-showdown/][The Great Theorem Prover Showdown]] ~ H. Wayne. #FormalMethods #Challenge #FunctionalProgramming
+ [[https://www.bbvaopenmind.com/tecnologia/inteligencia-artificial/la-deuda-de-la-inteligencia-artificial-con-el-matematico-godel/][La deuda de la Inteligencia Artificial con el matemático Gödel]] ~ J. Muñoz de la Cuesta. #Lógica #IA
+ [[https://arxiv.org/pdf/1908.07355.pdf][Knowledge distillation for semi-superviseddomain adaptation]] ~ M. Orbes-Arteaga. #SemiSupervisedLearning #DataDistillation
+ [[https://blogs.scientificamerican.com/cross-check/okay-maybe-proofs-arent-dying-after-all/][Okay, Maybe Proofs Aren't Dying After All]] ~ J. Horgan. #Mathematics #ITP
+ [[https://martinfowler.com/dsl.html][Domain-Specific Languages Guide]] ~ M. Fowler. #DSL
+ [[https://drive.google.com/file/d/19lv8p1fB47z1pEZVlfDXhop082Lc-kdD/view][Quantum supremacy using a programmable superconducting processor]] ~ Google AI Quantum and collaborators. #QuantumComputing
+ [[http://www.wisdom.weizmann.ac.il/~vision/DoubleDIP/resources/DoubleDIP.pdf][Double-DIP: Unsupervised Image Decomposition via Coupled Deep-Image-Priors]] ~ Y. Gandelsman #ImageSegmentation #DeepLearning 
+ [[https://towardsdatascience.com/review-dcn-deformable-convolutional-networks-2nd-runner-up-in-2017-coco-detection-object-14e488efce44][Review: DCN — Deformable Convolutional Networks, 2nd Runner Up in 2017 COCO Detection (Object Detection)]] ~ S-H. Tsang #DeepLearning #ObjectDetection #ImageSegmentation
+ [[https://arxiv.org/pdf/1907.08610v1.pdf][Lookahead Optimizer:k steps forward, 1 step back]] ~ M. R. Zhang. #MachineLearning #OptimizationAlgorithm
+ [[https://medium.com/sciforce/anomaly-detection-another-challenge-for-artificial-intelligence-c69d414b14db][Anomaly Detection — Another Challenge for Artificial Intelligence]] ~ Sciforce. #AnomalyDetection
+ [[https://towardsdatascience.com/enet-a-deep-neural-architecture-for-real-time-semantic-segmentation-2baa59cf97e9][ENet — A Deep Neural Architecture for Real-Time Semantic Segmentation]] ~ Arunava #SemanticSegmentation #DeepLearning 
+ [[http://zpascal.net/cvpr2017/Zendel_Analyzing_Computer_Vision_CVPR_2017_paper.pdf][Analyzing Computer Vision Data - The Good, the Bad and the Ugly]] ~ O. Zendel. #ComputerVision #Dasasets #Curation
+ [[https://cs.brown.edu/research/pubs/theses/masters/2011/vittayakorn.pdf][Quality Assessment for Crowdsourced Object Annotations]] ~ S. Vittayakorn. #ComputerVision #Dasasets #Quality
+ [[https://link.springer.com/article/10.1007/s11263-007-0090-8][LabelMe: A Database and Web-Based Tool for Image Annotation]] ~ B. C. Russell. #ObjectDetection #ImageAnnotation
+ [[https://www.cs.mcgill.ca/~jpineau/ReproducibilityChecklist.pdf][The Machine Learning Reproducibility Checklist]] ~ J. Pineau. #MachineLearning #Reproducibility
+ [[https://www.pnas.org/content/116/39/19251?utm_campaign=The%20Batch&utm_source=hs_email&utm_medium=email&utm_content=77292076&_hsenc=p2ANqtz--4jabhgaGYrDJ0iFw5Z2XaVnj_OqurXeZijBV9qWQXruQR3rGx2B0cifX_xtgnGbOPOaXo_VAzblyguUeoObly0AFGLA&_hsmi=77292076][Measuring actual learning versus feeling of learning in response to being actively engaged in the classroom]] ~ L. Deslauriers. #Teaching #ActiveMethodologies
+ [[https://blog.openmined.org/federated-learning-differential-privacy-and-encrypted-computation-for-medical-imaging/][Privacy-Preserving AI in Medical Imaging: Federated Learning, Differential Privacy, and Encrypted Computation]] ~ E. Bluemke. #ArtificialIntelligence #Privacy #FederatedLearning #DifferentialPrivacy #EncryptedComputation #MedicalImages 
+ [[https://openreview.net/forum?id=Bygh9j09KX][ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness]] ~ R. Geirhos. #ImageClassification #Robustness
+ [[https://arxiv.org/abs/1902.07208][Transfusion: Understanding Transfer Learning for Medical Imaging]] ~ M. Raghu. #TransferLearning #MedicalImages 
+ [[https://arxiv.org/pdf/1811.08883.pdf][Rethinking ImageNet Pre-training]] ~ K. He. #TransferLearning #ObjectDetection