@misc{lavoie2024modeling,
  title={Modeling Caption Diversity in Contrastive Vision-Language Pretraining},
  author={Samuel Lavoie and Polina Kirichenko and Mark Ibrahim and Mahmoud Assran and Andrew Gordon Wildon and Aaron Courville and Nicolas Ballas},
  year={2024},
  eprint={2405.00740},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2405.00740}
}