Awesome Robotics Manipulation · full_paper

ST-VLA: Enabling 4D-Aware Spatiotemporal Understanding for General Robot Manipulation

arXiv · 2026-03-14 · Low-Level Learning-Based Action Modelling / Input Modelling / 3D Vision Language Action Models

3D 表征VLA机器人学习操作
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Project
ST-VLA: Enabling 4D-Aware Spatiotemporal Understanding for General Robot Manipulation figure
AlphaXiv 中文论文页面（可滚动查看）