Flow to Learn: Flow Matching on Neural Network Parameters

Daniel Saragih, Deyu Cao, Tejas Balaji, Ashwin Santhosh

Published: 05 Mar 2025, Last Modified: 05 Mar 2025ICLR 2025 Workshop Weight Space Learning PosterEveryoneRevisionsBibTeXCC BY 4.0
Track: tiny / short paper (up to 4 pages)
Keywords: generative hyper-representation learning, conditional flow matching, meta-learning, neural network weights generation, few-shot learning
TL;DR: FLoWN, a latent flow matching model that learns to generate neural network parameters for different tasks through image conditioning.
Submission Number: 55