@article{chatvlaunifiedmultimodalunderstandingand,
  title = {ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model},
  author = {Zhongyi Zhou and Yichen Zhu and Minjie Zhu and Junjie Wen and Ning Liu and Zhiyuan Xu and Weibin Meng and Ran Cheng and Yaxin Peng and Chaomin Shen and Feifei Feng},
  year = {2025},
  eprint = {2502.14420},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.14420v2},
}