Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models

作者：Yanru Wu, Weiduo Yuan, Ang Qi, Vitor Guizilini, Jiageng Mao, Yue Wang · 单位：USC Physical Superintelligence Lab, Toyota Research Institute · 会议/期刊：arXiv · 日期：2026-03-17 · 来源：High-Level Structured Planning / Multimodal Reasoning / Reward Reasoning