@article{230609085v1,
  title = {COSA: Concatenated Sample Pretrained Vision-Language Foundation Model},
  author = {Sihan Chen and Xingjian He and Handong Li and Xiaojie Jin and Jiashi Feng and Jing Liu},
  year = {2023},
  eprint = {2306.09085},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2306.09085v1},
}