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

ArXi:2602.05951v2 Announce Type: replace-cross Flow matching has recently emerged as a promising alternative to diffusion-based generative models, particularly for text-to-image generation. Despite its flexibility in allowing arbitrary source distributions, most existing approaches rely on a standard Gaussian distribution, a choice inherited from diffusion models, and rarely consider the source distribution itself as an optimization target in such settings.