An instantiation of flow matching that relies on a time-independent velocity field to exactly map between two distributions, so long as the target is singular, is proposed and supported on a lower-dimensional data manifold.
Abstract
We propose an instantiation of flow matching that relies on a time-independent velocity field (an \emph{autonomous flow}) to exactly map between two distributions, so long as the target is singular, i.e.\ supported on a lower-dimensional data manifold. We also show that the one-step generative map associated with this flow is the unique solution of a simple conservation equation, which can be used to learn the map directly from samples. These autonomous flows and maps give a dynamical meaning to the flux constraint of Beckmann's transportation problem. Their construction provides a unifying framework that recovers, for instance, the closed-form Poisson-flow generative model and equilibrium matching with a quadratic flow-matching regression loss. We illustrate how this theory corrects inconsistencies in existing methods and demonstrate the effectiveness of the autonomous flow and the one-step map on ImageNet 256x256.
This paper analyzes the local Taylor expansion of a continuous denoiser to motivate a strict invariance condition required for optimal, singlestep generation: the conservation of target identity, and demonstrates that solving this condition via the Method of Characteristics analytically yields the straight-line traject...
Two lightweight, training-free algorithms are proposed, CAT-OV and CAT-OT that adapt step-sizes at inference time based on a novel connection between Flow Matching sampling and gradient flow that outperform existing step-size heuristics in image quality metrics across four text- to-image Flow Matching models.
Qinchan Li, Pedro Cisneros-Velarde, Ke-Ru Fu et al.· 1 citation
We introduce weighted Laplacian flow (WLF), a deterministic particle-flow framework for sampling from a target distribution known only up to normalization. The proposed method evolves the logarithmic density ratio through a transport equation and determines the particle velocity from a target-weighted Poisson problem,...
We introduce a new framework for one-step generative modelling on finite state spaces. To extend drifting beyond continuous domains, we use discrete Wasserstein geometry to define a target-relative KL gradient flow over the transitions of a reversible Markov kernel. We realize this probability flow at the particle leve...
Alessandro Micheli, Andrea Zerio, Samir Bhatt· 0 citations
A flow matching based algorithm is formulated which learns a transport map from the source to target trajectory distribution, while preserving the Markov structure, which is consistent in the population limit and derive finite-sample error bounds under mixing time assumptions.
Syamantak Kumar, D. Nagaraj, Saptarshi Roy et al.· 0 citations
We present the Variational Incompressible Optimal Transport (VIOT) operator, a generative neural operator for amortized incompressible density transport. Given a new source-target density pair, VIOT predicts a divergence-free velocity field and generates the full transport trajectory by feed-forward inference, replacin...
Jin-Jin He, Shenyifan Lu, Si-Nan Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
