@article{revisitlargescaleimagecaptiondatainpre,
  title = {Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models},
  author = {Zhengfeng Lai and Vasileios Saveris and Chen Chen and Hong-You Chen and Haotian Zhang and BoWen Zhang and Juan Lao Tebar and Wenze Hu and Zhe Gan and Peter Grasch and Meng Cao and Yinfei Yang},
  year = {2024},
  eprint = {2410.02740},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.02740v1},
}