Awesome Robotics Manipulation · full_paper

ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models

arXiv · 2026-02-20 · 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
ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models figure
AlphaXiv 中文论文页面（可滚动查看）