RISE: Self-Improving Robot Policy with Compositional World Model
Paper • 2602.11075 • Published • 29
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("OpenDriveLab-org/RISE_Assets", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]🌏 RISE
Please refer to RISE repo for detailed instructions.
🔥 Highlights
- 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. Large performance improvements on challenging dexterous tasks, including +35% on dynamic brick sorting, +45% on backpack packing, and +35% on box closing.
📢 News
- [2026/04/22] Training code and pre-trained dynamics model are released.
- [2026/02/11] Paper released on arXiv.
📄 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.
@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}
}
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support