Awesome Robotics Manipulation · full_paper

SA-VLA: Spatially-Aware Flow-Matching for Vision-Language-Action Reinforcement Learning

arXiv · 2026-01-31 · Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with RL

强化学习VLA触觉机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
SA-VLA: Spatially-Aware Flow-Matching for Vision-Language-Action Reinforcement Learning figure
AlphaXiv 中文论文页面（可滚动查看）