---
title: MosIT
author: Anonym
date: 2023-09-11 00:00:00 +0800
categories: [ICLR 2024]
tags: [IT Dataset]
math: true
pin: false
---

- Paper: [NExT-GPT: Any-to-Any Multimodal LLM](https://arxiv.org/abs/2309.05519)
- [GitHub Link](https://next-gpt.github.io/)
- Publisher: `ICLR 2024`
- Author Affiliation: `National University of Singapore`
- Type
  + [x] SFT
  + [ ] RLHF
- Multi-turn
  + [x] ✔
  + [ ] ✖
- Input Modalities $\rightarrow$ Output Modalities <br />(I: Image, V: Video, A: Audio, 3D: Point Cloud, T: Text, B: Bounding box, Tab: Table, Web: Web page)
  + I+V+A+T $\rightarrow$ I+V+A+T
- Source
  + `Youtube, Google, Flickr30k, Midjourney, etc.`
- Method
  + `Auto. + Manu.`
- I/V/A Scale
  + I
    * `4K`
  + V
    * `4K`
  + A
    * `4K`
- Dialog Turn
  + `4.8`
- Instance Scale
  + `5K`