@misc{basu2023augmenting,
  title={Augmenting CLIP with Improved Visio-Linguistic Reasoning},
  author={Samyadeep Basu and Maziar Sanjabi and Daniela Massiceti and Shell Xu Hu and Soheil Feizi},
  year={2023},
  eprint={2307.09233},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2307.09233}
}