SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shen, Zhenyi, Lu, Junru, Gui, Lin, Li, Jiazheng, He, Yulan, Yin, Di, Sun, Xing
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2511.20102