The Generation Phases of Flow Matching: a Denoising Perspective
This work addresses a fundamental gap in understanding flow matching for researchers, but it is incremental as it builds on existing methods without introducing a new paradigm.
The paper tackled the problem of understanding the generation process in flow matching models by adopting a denoising perspective, and it resulted in new insights into distinct dynamical phases and precise characterization of denoiser performance during generation.
Flow matching has achieved remarkable success, yet the factors influencing the quality of its generation process remain poorly understood. In this work, we adopt a denoising perspective and design a framework to empirically probe the generation process. Laying down the formal connections between flow matching models and denoisers, we provide a common ground to compare their performances on generation and denoising. This enables the design of principled and controlled perturbations to influence sample generation: noise and drift. This leads to new insights on the distinct dynamical phases of the generative process, enabling us to precisely characterize at which stage of the generative process denoisers succeed or fail and why this matters.