Conditional Flow Matching

Follow this topic Ask about this topic

Momentum

10 papers in the last four weeks, up 233% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 36

All topics

Coreset-Induced Conditional Velocity Flow Matching
May 13, 2026Xiao Wang, Zihua She, Jianxi SuConditional Flow Matching Rectified Flow
Department of Statistics, Purdue University
Quantile-Coupled Flow Matching for Distributional Reinforcement Learning
May 8, 2026Michael Groom, Victor-Alexandru Darvariu, Lars Kunze +2Distributional RL Conditional Flow Matching
Oxford Robotics Institute, University of Oxford, Oxford, United Kingdom · Bristol Robotics Laboratory, University of the West of England, Bristol, United Kingdom · Dyson Institute of Engineering & Technology, Malmesbury, United Kingdom
Flow Matching with Arbitrary Auxiliary Paths
May 7, 2026Xin Peng, Ang GaoConditional Flow Matching Flow-Based Generative Modeling
School of Physical Science and Technology, Beijing University of Posts and Telecommunications, Beijing, China
Deep Learning for Model Calibration in Simulation of Itaconic Acid Production
Apr 24, 2026Daria Fokina, Marco Baldan, Constantin Romankiewicz +3Conditional Flow Matching Nonlinear System Identification
Fraunhofer ITWM, Kaiserslautern, Germany · RPTU Kaiserslautern, Kaiserslautern, Germany
ScatterPrism: convergence for generative simulation and inverse problems in particle and nuclear physics
Apr 1, 2026Zeyu Xia, Tyler Kim, Trevor Reed +3Surrogate Modeling Conditional Flow Matching
Department of Computer Science, University of Virginia, 85 Engineer’s Way, Charlottesville, VA 22904, USA · School of Data Science, University of Virginia, 1919 Ivy Road, Charlottesville, VA 22903, USA · Department of Physics, Indiana University Bloomington, 727 East Third Street, Bloomington, IN 47405, USA
Conditional Flow Matching for Visually-Guided Acoustic Highlighting
Feb 3, 2026Hugo Malard, Gael Le Lan, Daniel Wong +3Conditional Flow Matching Audio-Visual Alignment
LTCI, Télécom Paris, Institut Polytechnique de Paris · Meta

May 13, 2026, stat.MLJ/K move · Enter open · S save

Coreset-Induced Conditional Velocity Flow Matching

Xiao Wang, Zihua She, Jianxi Su

Department of Statistics, Purdue University

Conditional Flow Matching Rectified Flow Flow-Based Generative Modeling Conditional Generative Modeling

Open paper AskPDF arXiv

We propose Coreset-Induced Conditional Velocity Flow Matching (CCVFM), a generative model that augments hierarchical rectified flow with a data-informed source distribution. Hierarchical flow matching models the full conditional velocity law in velocity space, but its inner flow is asked to transport isotropic Gaussian noise to a multimodal target velocity distribution from scratch. Our key observation is that this inner source can be replaced by a closed-form surrogate built from a coreset of the target. CCVFM first compresses the target into weighted atoms using an entropic Sinkhorn coreset and lifts them to a Gaussian mixture. The induced conditional velocity law is then a closed-form Gaussian mixture that can be sampled without a learned neural sampler. A lightweight correction flow, trained from this exact surrogate source, then refines the remaining surrogate-to-target residual rather than learning an entire noise-to-data map. We prove that the surrogate transport cost equals the target--surrogate Wasserstein gap under an explicit compression assumption, whereas the noise-source analogue has a dimension-scale lower bound. We further characterize the conditional second moment of the direct surrogate-source training target and show that its source-dependent excess is small when the surrogate conditional law is close to the true conditional velocity law in mean and covariance. Empirically, on MNIST, CIFAR-10, ImageNet-32, and CelebA-HQ, the proposed method reaches competitive few-step generation under matched architectures.

Momentum

Related topics

Latest papers 36

Coreset-Induced Conditional Velocity Flow Matching

Quantile-Coupled Flow Matching for Distributional Reinforcement Learning

Flow Matching with Arbitrary Auxiliary Paths

Deep Learning for Model Calibration in Simulation of Itaconic Acid Production

ScatterPrism: convergence for generative simulation and inverse problems in particle and nuclear physics

Conditional Flow Matching for Visually-Guided Acoustic Highlighting