---
license: apache-2.0
tags:
- world model
- latent action
- decision making
- robot learning
- video generation
---

## Introduction

**TL;DR:** We pretrain AdaWorld with continuous latent actions from thousands of environments, making it highly efficient for action transfer, world model adaptation, and visual planning, even with minimal interactions and finetuning steps.

- Project page: https://adaptable-world-model.github.io
- Paper: https://arxiv.org/abs/2503.18938
- Code: https://github.com/Little-Podi/AdaWorld

## How to Use

Check out https://github.com/Little-Podi/AdaWorld

## Citation

```bibtex
@article{gao2025adaworld,
  title={AdaWorld: Learning Adaptable World Models with Latent Actions}, 
  author={Gao, Shenyuan and Zhou, Siyuan and Du, Yilun and Zhang, Jun and Gan, Chuang},
  journal={arXiv preprint arXiv:2503.18938},
  year={2025}
}
```

## Contact

If you have any questions or comments, feel free to contact me through email sygao@connect.ust.hk