@article{multimodaladaptivedistillationfor,
  title = {Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks},
  author = {Zhecan Wang and Noel Codella and Yen-Chun Chen and Luowei Zhou and Xiyang Dai and Bin Xiao and Jianwei Yang and Haoxuan You and Kai-Wei Chang and Shih-Fu Chang and Lu Yuan},
  year = {2022},
  eprint = {2204.10496},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2204.10496v2},
}