@inproceedings{whenattentionmeetsfastrecurrencetraining,
  title = {When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute},
  author = {Tao Lei},
  year = {2021},
  booktitle = {EMNLP 2021 11},
  eprint = {2102.12459},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2102.12459v3},
}