@article{mlparchitecturesforvisionandlanguage,
  title = {MLP Architectures for Vision-and-Language Modeling: An Empirical Study},
  author = {Yixin Nie and Linjie Li and Zhe Gan and Shuohang Wang and Chenguang Zhu and Michael Zeng and Zicheng Liu and Mohit Bansal and Lijuan Wang},
  year = {2021},
  eprint = {2112.04453},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2112.04453v1},
}