WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL

作者：Zhennan Jiang, Shangqing Zhou, Yutong Jiang, Zefang Huang, Mingjie Wei, Yuhui Chen, Tianxing Zhou, Zhen Guo, Hao Lin, Quanlu Zhang, Yu Wang, Haoran Li, Chao Yu, Dongbin Zhao, Equal contribution Corresponding authors · 单位：Tsinghua university, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Zhongguancun Academy · 会议/期刊：arXiv · 日期：2026-02-15 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Auxiliary Tasks - World Model & Visual Prediction / World Model