notesum.ai

Published at October 18

Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection

cs.CL
cs.AI
cs.LG

Released Date: October 18, 2024

Authors: Aaron Alvarado Kristanto Julistiono, Davoud Ataee Tarzanagh1, Navid Azizan2

Aff.: 1University of Pennsylvania; 2Massachusetts Institute of Technology

Arxiv: https://arxiv.org/abs/2410.14581v1