Awesome Robotics Manipulation · full_paper

RoboReward: General-Purpose Vision-Language Reward Models for Robotics

作者：Tony Lee · 单位：Stanford University, UC Berkeley · 会议/期刊：arXiv · 日期：2026-01-02 · 来源：High-Level Structured Planning / Multimodal Reasoning / Reward Reasoning

任务规划多模态推理强化学习感知操作
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Project
RoboReward: General-Purpose Vision-Language Reward Models for Robotics figure
AlphaXiv 中文论文页面（可滚动查看）