La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse Activation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Kai, Xu, Bowen, Wu, Shaoyu, Chen, Xin, Zhou, Hao, Tao, Yongliang, Hu, Lulu
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/2507.01299