Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Yingfa, Thai, Zhen Leng, Zhou, Zihan, Zhang, Zhu, Shen, Xingyu, Wang, Shuo, Xiao, Chaojun, Han, Xu, Liu, Zhiyuan
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2601.22156