Awesome Robotics Manipulation · full_paper

ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning

作者：Hanyang Chen, Mark Zhao, Rui Yang, Qinwei Ma, Ke Yang, Jiarui Yao, Kangrui Wang, Hao Bai, Zhenhailong Wang, Rui Pan, Mengchao Zhang, Jose Barreiros, Aykut Onol, ChengXiang Zhai, Heng Ji, Manling Li, Huan Zhang, Tong Zhang · 单位：UIUC, Northwestern University, Toyota Research Institute · 会议/期刊：arXiv · 日期：2025-10-14 · 来源：High-Level Structured Planning / Multimodal Reasoning / Robot Reasoning

任务规划多模态推理强化学习触觉语言条件
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning figure
AlphaXiv 中文论文页面（可滚动查看）