RACE Attention: A Strictly Linear-Time Attention Layer for Training on Outrageously Large Contexts

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Joshi, Sahil, Chowdhury, Agniva, Kanakamedala, Amar, Singh, Ekam, Tu, Evan, Shrivastava, Anshumali
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.04008