@article{visionlanguageactionmodelwithopenworld,
  title = {ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge},
  author = {Zhongyi Zhou and Yichen Zhu and Junjie Wen and Chaomin Shen and Yi Xu},
  year = {2025},
  eprint = {2505.21906},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.21906v2},
}