baiyu858/Bridge-WA-World-Teacher-VLABench

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

This repository contains the policy checkpoint for Bridge-WA evaluated on VLABench, as presented in Bridge-WA: Predicting Where and How the World Changes for Robotic Action.

• Project Page: https://hcplab-sysu.github.io/BRIDGE-WA
• Repository: https://github.com/HCPLab-SYSU/BRIDGE-WA

Introduction

Bridge-WA is a lightweight world-action framework that distills a frozen future-change teacher into three compact priors: future tokens for intended outcomes, change maps for intervention support, and motion-flow maps for local transition direction. A WorldBridge conditions the action transformer on these priors through multi-source attention memories and spatial-temporal biases, while the teacher model is removed at inference.

Citation

@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}
}