notesum.ai

Published at October 29

Fourier Head: Helping Large Language Models Learn Complex Probability Distributions

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

Released Date: October 29, 2024

Authors: Nate Gillman1, Daksh Aggarwal1, Michael Freeman1, Saurabh Singh2, Chen Sun3

Aff.: 1Brown University; 2Google DeepMind; 3Brown University, Google DeepMind

Arxiv: https://arxiv.org/abs/2410.22269v1