Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[RSS 2026] Code for RISE: Self-Improving Robot Policy with Compositional World Model
| Date | Stars |
|---|---|
| 2026-07-24 | 326 |
| 2026-07-25 | 327 |
| 2026-07-28 | 329 |
| 2026-07-30 | 329 |
| 2026-08-06 | 329 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# 🌏 RISE
<div id="top" align="left">
<a href="https://opendrivelab.com/rise/"><img src="https://img.shields.io/badge/Proj_Page-blue" alt="Project Page"></a>
<a href="https://arxiv.org/abs/2602.11075"><img src="https://img.shields.io/badge/arXiv-2602.11075-b31b1b" alt="arXiv"></a>
<a href="https://x.com/jiazhi_yang2024/status/2022247675060797636"><img src="https://img.shields.io/badge/summary-000000?logo=x&logoColor=white" alt="X"></a>
</div>
<img src="rise_assets/teaser.gif" alt="RISE demo" width="100%">
</img>
## 📢 News
- **`2026/Jun/03`** ❗❗❗ Please pull the latest code for important bug fixes.
- **`2026/Mar/27`** 🚀 RISE got accepted to RSS 2026.
- **`2026/Mar/22`** Training code and pre-trained dynamics model are released.
- **`2026/Feb/11`** Paper released on [arXiv](https://arxiv.org/abs/2602.11075).
## 🔥 Highlights
<!-- RISE is a self-improving robot policy framework that turns world models into a practical learning environment for real-world manipulation. In short, we make the following three key contributions: -->
- **A compositional world model.**
A principled design that combines a controllable multi-view dynamics model with a progress value model, yielding informative advantages for robust policy improvement.
- **RL in imagination.**
A scalable self-improving framework that bootstraps robot policies through imaginary rollouts, avoiding the hardware cost and laborious reset of real-world interactions.
- **Real-world manipulation gains.**
Non-trivial performance improvements on challenging dexterous tasks, including +35% on dynamic brick sorting, +45% on backpack packing, and +35% on box closing.
## 🗺️ Overview
RISE repository is structured with three major parts:
- `policy_and_value/policy_offline_and_value`: OpenPI-based offline policy and value training. They are put together since they share similar model architecture and training pipeline.
- `dynamics/dynamics_model`: Action-conditioned dynamics model.
- `policy_and_value/policy_online`: Online RL for policy improvement.
## 🧑💻 Getting Started
- [💻 Installation](docs/installation.md)
- [🏆 Offline Policy Training & Value Model](docs/offline_learning.md)
- [🔮 Dynamics Model](docs/dynamics_model.md)
- [🦾 Online Policy Training](docs/online_training.md)
- [🛠️ Deployment on Piper](docs/deploy.md)
## ❤️ Acknowledgement
We thank the following projects for their open-source contributions: [OpenPI Pi0 / Pi05](https://github.com/openpi/openpi), [Genie Envisioner](https://github.com/AgibotTech/Genie-Envisioner), [RLinf](https://github.com/RLinf/RLinf), [LTX-Video](https://github.com/Lightricks/LTX-Video), [Kai0](https://github.com/OpenDriveLab/kai0).
## 📄 License and Citation
All assets and code in this repository are under the Apache 2.0 license unless specified otherwise. The data and checkpoint are under CC BY-NC-SA 4.0. Other modules inherit their own distribution licenses.
```bibtex
@article{rise2026,
title={RISE: Self-Improving Robot Policy with Compositional World Model},
author={Yang, Jiazhi and Lin, Kunyang and Li, Jinwei and Zhang, Wencong and Lin, Tianwei and Wu, Longyan and Su, Zhizhong and Zhao, Hao and Zhang, Ya-Qin and Chen, Li and Luo, Ping and Yue, Xiangyu and Li, Hongyang},
journal={arXiv preprint arXiv:2602.11075},
year={2026}
}
```
[](https://star-history.com/#OpenDriveLab/RISE&Date)
Excerpt of 3,454 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:917a00a952a6a8c4, topic:manipulation, readme:manipulation
matched fp:917a00a952a6a8c4, topic:diffusion-models
matched fp:917a00a952a6a8c4, topic:vision-language-model