Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mi, Zhendong, Chen, Yixiao, Zhao, Pu, Yu, Xiaodong, Wang, Hao, Wang, Yanzhi, Huang, Shaoyi
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.09316