Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Ziyang, Ding, Tianjiao, Lu, Yifu, Pai, Druv, Zhang, Jingyuan, Wang, Weida, Yu, Yaodong, Ma, Yi, Haeffele, Benjamin D.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!