Superiority of Softmax: Unveiling the Performance Edge Over Linear Attention

Yichuan Deng, Zhao Song, Tianyi Zhou
October, 2023
PDF Cite
Type
Preprint
Publication
arXiv preprint arXiv:2310.11685
Yichuan Deng
Yichuan Deng
Ph.D. Student in Computer Science

My research interests lay in Theoretical Computer Science.