@misc{multimodalityvlt52021,
  title = {{Unifying Vision-and-Language Tasks via Text Generation}},
  author = {Jaemin Cho and Jie Lei and Hao Tan and Mohit Bansal},
  year = {2021},
  eprint = {2102.02779},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2102.02779}
}
