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
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026