notesum.ai

Published at November 8

Aioli: A Unified Optimization Framework for Language Model Data Mixing

cs.LG
cs.AI
cs.CL
stat.ML

Released Date: November 8, 2024

Authors: Mayee F. Chen1, Michael Y. Hu2, Nicholas Lourie3, Kyunghyun Cho4, Christopher Ré1

Aff.: 1Department of Computer Science, Stanford University; 2Center for Data Science, New York University; 3Computer Science Department, New York University; 4Computer Science Department, New York University, Prescient Design, Genentech

Arxiv: http://arxiv.org/abs/2411.05735v1