Awesome Robotics Manipulation · full_paper

3D-Mix for VLA: A Plug-and-Play Module for Integrating VGGT-based 3D Information into Vision-Language-Action Models

arXiv · 2026-03-25 · 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 Code
3D-Mix for VLA: A Plug-and-Play Module for Integrating VGGT-based 3D Information into Vision-Language-Action Models figure
AlphaXiv 中文论文页面（可滚动查看）