@article{multimodalpretrainingformedicalvision,
  title = {Multi-modal Pre-training for Medical Vision-language Understanding and Generation: An Empirical Study with A New Benchmark},
  author = {Li Xu and Bo Liu and Ameer Hamza Khan and Lu Fan and Xiao-Ming Wu},
  year = {2023},
  eprint = {2306.06494},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2306.06494v2},
}