@article{visionlanguagefoundationmodelsas,
  title = {Vision-Language Foundation Models as Effective Robot Imitators},
  author = {Xinghang Li and Minghuan Liu and Hanbo Zhang and Cunjun Yu and Jie Xu and Hongtao Wu and Chilam Cheang and Ya Jing and Weinan Zhang and Huaping Liu and Hang Li and Tao Kong},
  year = {2023},
  eprint = {2311.01378},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.01378v3},
}