Awesome Robotics Manipulation · full_paper

M2-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills

arXiv · 2026-04-27 · Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / PEFT

VLA泛化机器人学习操作
新标签打开 AlphaXiv新标签打开 Paper
M2-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills figure
AlphaXiv 中文论文页面（可滚动查看）