@article{improvingautoregressivenlptasksvia,
  title = {Improving Autoregressive NLP Tasks via Modular Linearized Attention},
  author = {Victor Agostinelli and Lizhong Chen},
  year = {2023},
  eprint = {2304.08453},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2304.08453v3},
}