RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Model

作者：Mingtong Dai, Lingbo Liu, Yongjie Bai, Yang Liu, Zhouxia Wang, Rui Su, Chunjie Chen, Liang Lin, Xinyu Wu · 单位：Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Peng Cheng Laboratory, School of Computer Science and Engineering, Sun Yat-sen University, College of Computing and Data Science, Nanyang Technological University, Shanghai AI Laboratory, University of Chinese Academy of Sciences, X-Era AI Lab · 会议/期刊：arXiv · 日期：2025-10-13 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Model-agnostic Strategies