Publication

Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching

A method that learns condition-dependent source distributions for flow matching, enabling straighter transport paths and up to 3x faster convergence.

AUTHORS Junwan Kim*, Jiho Park*, Seonghu Jeon, Seungryong Kim
MY ROLE Research Contributor
VENUE Under Review
DATE January 2026
LINKS Paper · Project Page · arXiv · PDF · Code

Contents

  1. Abstract
  2. Links

Abstract

We introduce a method for learning condition-dependent source distributions in flow matching frameworks. Standard flow matching uses a fixed Gaussian as the source distribution, leading to curved transport paths and slow convergence. By adapting the source distribution based on the target condition, our approach achieves straighter trajectories, reduced variance, and up to 3x faster convergence in FID compared to standard Gaussian source distributions.