@article{diffuserefficienttransformerswithmulti, title = {Diffuser: Efficient Transformers with Multi-hop Attention Diffusion for Long Sequences}, author = {Aosong Feng and Irene Li and Yuang Jiang and Rex Ying}, year = {2022}, eprint = {2210.11794}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2210.11794v2}, }