Awesome Robotics Manipulation · full_paper

OmniVLA-RL: A Vision-Language-Action Model with Spatial Understanding and Online RL

作者：Haoxiang Jie, Yaoyuan Yan, Xiangyu Wei, Kailin Wang, Hongjie Yan, Zhiyou Heng, Daocheng Chen · 单位：AI Lab, Country Garden Services, East China Normal University · 会议/期刊：arXiv · 日期：2026-04-20 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with RL

视觉语言动作机器人学习
新标签打开 AlphaXiv新标签打开 Paper
OmniVLA-RL: A Vision-Language-Action Model with Spatial Understanding and Online RL figure
AlphaXiv 中文论文页面（可滚动查看）