Awesome Robotics Manipulation · full_paper

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

arXiv · 2026-03-17 · High-Level Structured Planning / Multimodal Reasoning / Reward Reasoning

任务规划多模态推理强化学习泛化
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Project
Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models figure
AlphaXiv 中文论文页面（可滚动查看）