Sub-Token Routing in LoRA for Adaptation and Query-Aware KV Compression

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Wei, Wang, Wei
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computation and Language 68W99, 68W40
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.21335