@article{transformerwithamixtureofgaussiankeys1,
  title = {Improving Transformers with Probabilistic Attention Keys},
  author = {Tam Nguyen and Tan M. Nguyen and Dung D. Le and Duy Khuong Nguyen and Viet-Anh Tran and Richard G. Baraniuk and Nhat Ho and Stanley J. Osher},
  year = {2021},
  eprint = {2110.08678},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2110.08678v2},
}