The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Saponati, Matteo, Sager, Pascal, Aceituno, Pau Vilimelis, Stadelmann, Thilo, Grewe, Benjamin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!