@article{chainofmodalitylearningmanipulation,
  title = {Chain-of-Modality: Learning Manipulation Programs from Multimodal Human Videos with Vision-Language-Models},
  author = {Chen Wang and Fei Xia and Wenhao Yu and Tingnan Zhang and Ruohan Zhang and C. Karen Liu and Li Fei-Fei and Jie Tan and Jacky Liang},
  year = {2025},
  eprint = {2504.13351},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.13351v1},
}