Awesome Robotics Manipulation · full_paper

Pri4R: Learning World Dynamics for Vision-Language-Action Models with Privileged 4D Representation

arXiv · 2026-03-02 · Low-Level Learning-Based Action Modelling / Input Modelling / 3D Vision Language Action Models

3D 表征VLA机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Project
Pri4R: Learning World Dynamics for Vision-Language-Action Models with Privileged 4D Representation figure
AlphaXiv 中文论文页面（可滚动查看）