Hidden Heroes and Gradient Bloats: Layer-Wise Redundancy Inverts Attribution in Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Ye, Donald
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.01442