Attention Editing: A Versatile Framework for Cross-Architecture Attention Conversion

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cheng, Zhen, Yang, Hao-Bo, Huang, Wan-Yi, Li, Jin-Long
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.05688