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

@misc{xiao2026mvla,
  title = {M2-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills},
  author = {Si-Yao Xiao and Yuhong Zhang and Zhi-Fang Liu and Zi-Han Gao and Jingyu Zhang and Sin-Young Choo and Da-Ke Zhong and Meng-Zhen Wang and Xiaoyi Lin and Xian Zhou and Jianchao Jia and Haoqian Wang},
  year = {2026},
  eprint = {2604.24182},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.24182},
}