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

作者：Yuhong Zhang, Zhifang Liu, Zihan Gao, Jingye Zhang, Sinwai Choo, Dake Zhong, Mengzhe Wang, Xiao Lin, Xianfeng Zhou, Jia Jia, Haoqian Wang · 单位：Tsinghua Shenzhen International Graduate School, Tsinghua University, Peng Cheng Laboratory, Shenzhen, China, College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China · 会议/期刊：arXiv · 日期：2026-04-27 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / PEFT