Bridge-WA: Predicting Where and How the World Changes for Robotic Action

Bridge-WA is a lightweight world-action framework that distills a frozen future-change teacher into compact world-change priors (future tokens, change maps, and motion-flow maps) to guide robotic action generation.

Citation

If you find Bridge-WA useful in your research, please cite:

@article{bai2026bridgewa,
  title   = {Bridge-WA: Predicting Where and How the World Changes for Robotic Action},
  author  = {Bai, Yongjie and Wang, Hanting and Dai, Mingtong and Zhong, Qijun and Liu, Yang and Lin, Liang},
  year    = {2026}
}
Downloads last month
28
Safetensors
Model size
1B params
Tensor type
F32
·
Video Preview
loading

Paper for baiyu858/Bridge-WA-VLABench