Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Vendrell, Victor Conchello, Masdemont, Arnau Padres, Grillo, Niccolò, Ros-Giralt, Jordi, Behboodi, Arash, Massoli, Fabio Valerio
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2605.07721