@article{trainingvisionlanguagemodelswithless,
  title = {Training Vision-Language Models with Less Bimodal Supervision},
  author = {Elad Segal and Ben Bogin and Jonathan Berant},
  year = {2022},
  eprint = {2211.00262},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2211.00262v1},
}