@article{otteravisionlanguageactionmodelwith,
  title = {OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction},
  author = {Huang Huang and Fangchen Liu and Letian Fu and Tingfan Wu and Mustafa Mukadam and Jitendra Malik and Ken Goldberg and Pieter Abbeel},
  year = {2025},
  eprint = {2503.03734},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.03734v3},
}