Cite
Notes
Only stored in your browser.
Attribution
Native Hybrid Attention for Efficient Sequence Modeling
arXiv 2025
Speed Always Wins: A Survey on Efficient Architectures for Large Language Models
Liger: Linearizing Large Language Models to Gated Recurrent Structures
from 3 papers
Jiaxi Hu
Weigao Sun
Yu Cheng
Disen Lan
Daizong Liu
Guoqi Li
Kexin Wang
Tao Zhang
Tong Zhu
Wenliang Chen