# 🌌 DreamX-Phi

**DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation**

[![arXiv](https://img.shields.io/badge/arXiv-2608.13489-b31b1b.svg?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2608.13489)

DreamX-Phi is a geometry-aware video world model built on Wan2.2-TI2V-5B.
Given an initial observation and a prescribed robot action sequence, it predicts
the corresponding future video while preserving robot motion, scene geometry,
and the state of the manipulated object.

## ✨ Highlights

- Geometry-aware action conditioning for end-effector poses and gripper states.
- Interaction-aware learning for coherent scene and object evolution.
- DMD-based few-step generation for efficient inference.
- First place on WorldArena 2.0 Track 1 and tied for second on Track 2.

## 🚀 Release

Model weights and inference code will be made publicly available after the
WorldArena 2.0 IROS Challenge concludes.

## 📖 Citation

Read the technical report on [arXiv](https://arxiv.org/abs/2608.13489). If you
find this work useful, please cite:

```bibtex
@misc{dreamxteam2026dreamxphi10actionconditionedvideo,
  title         = {DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation},
  author        = {DreamX Team and Rui Chen and Xiangxiang Chu and Geng Li and Jifan Li and Qingfeng Shi and Datao Tang and Jing Tang and Jun Wang and Pengfei Zhang},
  year          = {2026},
  eprint        = {2608.13489},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CV},
  url           = {https://arxiv.org/abs/2608.13489}
}
```

## 📄 License

This repository is released under the [MIT License](LICENSE).