Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kohli, Harsh, Parthasarathy, Srinivasan, Sun, Huan, Yao, Yuekun
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/2604.07822