@article{distillinginternetscalevisionlanguage,
  title = {Distilling Internet-Scale Vision-Language Models into Embodied Agents},
  author = {Theodore Sumers and Kenneth Marino and Arun Ahuja and Rob Fergus and Ishita Dasgupta},
  year = {2023},
  eprint = {2301.12507},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2301.12507v2},
}