Optimal Transport Flow Matching by Design

• URL: http://arxiv.org/abs/2606.04092v1
• Date: Tue, 02 Jun 2026 18:00:05 GMT
• Title: Optimal Transport Flow Matching by Design
• Abstract summary: Flow matching models learn to transport samples from a simple prior distribution to a complex data distribution.<n>We reformulate the problem by treating the prior as a design choice rather than a fixed input.<n>Our method reduces trajectory curvature by more than $2times$ compared to existing flow matching methods.
• Score: 26.301026025241374
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Flow matching models learn to transport samples from a simple prior distribution to a complex data distribution. When prior-data pairs are coupled via optimal transport (OT), the learned trajectories are straight and non-crossing, enabling fast, even single-step, generation. However, computing the OT coupling in high dimensions is intractable, and existing methods attempt to solve the OT problem, at the cost of persistent bias or significant overhead. Rather than solving for the OT coupling, we reformulate the problem. Once the prior is treated as a design choice rather than a fixed input, the OT coupling between prior and data is no longer unique. Many priors admit an OT-optimal identity coupling to the data, leaving us free to choose one that is also tractable to sample. We identify low-frequency projection of natural images as such a choice. The identity coupling between data and its low-frequency representation is empirically OT-optimal, the prior is structured enough to be sampled by a lightweight model at inference, and the remaining flow-matching task reduces to synthesizing high-frequency detail. Interpolating the prior with Gaussian noise further improves generation quality while preserving the OT coupling. The approach requires no modifications to the flow model itself, and integrates naturally with latent-space models, classifier-free guidance, and one-step generation frameworks. Across all benchmarks, our method reduces trajectory curvature by more than $2\times$ compared to existing flow matching methods, yielding better generation quality in the few-step regime.

Related papers

• One-Sided Quantile Coupling for Flow Matching [8.295726579539016]
  Flow Matching trains continuous-time generative models by regressing the velocity field of a probability path between a simple source distribution and a target data distribution.<n>We propose Quantile Coupling Flow Matching (QC-FM), a lightweight one-sided coupling that samples only the data batch and constructs each paired source directly.<n>QC-FM improves over the Baseline under matched training budgets, reducing FID by up to 12.9%, and outperforms OT-CFM on all four datasets.
  arXiv  Detail & Related papers  (2026-08-02T04:03:59Z)
• Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models [56.67321805551389]
  Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators.<n>The sampler, controlling the exploration behavior and denoising dynamics, is thus part of the policy.<n>We propose a new sampler that balances effective exploration with stability.
  arXiv  Detail & Related papers  (2026-05-22T11:37:22Z)
• QDSB: Quantized Diffusion Schrödinger Bridges [4.3331379059769395]
  We propose quantized diffusion Schrdinger bridges (QDSB), which compute the endpoint coupling on anchor-quantized endpoint distributions.<n>We show that the regularized optimal coupling is stable w.r.t. anchor quantization, with an error controlled by the quality of the anchor approximation.
  arXiv  Detail & Related papers  (2026-05-12T11:35:08Z)
• Coupling Models for One-Step Discrete Generation [50.37847093567075]
  Coupling Models is a one-step discrete generative model that learns a direct coupling between discrete sequences and Gaussian latents.<n>It avoids complex continuous flows over the simplex and hand-specified data-to-noise couplings.<n>It reduces LM1B text-generation perplexity by 33% at its lowest-perplexity operating point.
  arXiv  Detail & Related papers  (2026-05-08T03:40:39Z)
• ODE-free Neural Flow Matching for One-Step Generative Modeling [4.319549155064877]
  Diffusion and flow matching models generate samples by learning time-dependent vector fields whose integration transports noise to data.<n>We propose Optimal Transport Neural Flow Matching (OT-NFM), an ODE-free generative framework that parameterizes the flow map with neural flows.<n>We show that naive flow-map training suffers from mean collapse, where inconsistent noise-data pairings drive all outputs toward the data mean.
  arXiv  Detail & Related papers  (2026-04-07T19:49:57Z)
• Temporal Pair Consistency for Variance-Reduced Flow Matching [13.328987133593154]
  Temporal Pair Consistency (TPC) is a lightweight variance-reduction principle that couples velocity predictions at paired timesteps along the same probability path.<n>Instantiated within flow matching, TPC improves sample quality and efficiency across CIFAR-10 and ImageNet at multiple resolutions.
  arXiv  Detail & Related papers  (2026-02-04T00:05:21Z)
• Trajectory Consistency for One-Step Generation on Euler Mean Flows [24.038760671907024]
  We propose emphEuler Mean Flows (EMF), a flow-based generative framework for one-step and few-step generation.<n>EMF enforces long-range trajectory consistency with minimal sampling cost.
  arXiv  Detail & Related papers  (2026-01-31T04:32:32Z)
• Preference Trajectory Modeling via Flow Matching for Sequential Recommendation [50.077447974294586]
  Sequential recommendation predicts each user's next item based on their historical interaction sequence.<n>FlowRec is a simple yet effective sequential recommendation framework.<n>We construct a personalized behavior-based prior distribution to replace Gaussian noise and learn a vector field to model user preference trajectories.
  arXiv  Detail & Related papers  (2025-08-25T02:55:42Z)
• ReDi: Rectified Discrete Flow [17.72385262464804]
  We analyze the factorization approximation error using Conditional Total Correlation (TC)<n>We propose Rectified Discrete Flow (ReDi), a novel iterative method that reduces the underlying factorization error.<n> Empirically, ReDi significantly reduces Conditional TC and enables few-step generation.
  arXiv  Detail & Related papers  (2025-07-21T01:18:44Z)
• Beyond Optimal Transport: Model-Aligned Coupling for Flow Matching [59.97254029720877]
  Flow Matching (FM) is an effective framework for training a model to learn a vector field that transports samples from a source distribution to a target distribution.<n>We propose Model- Coupling Coupling (MAC), an effective method that matches training couplings based on geometric distance.<n>Experiments show that MAC significantly improves generation quality and efficiency in few-step settings compared to existing methods.
  arXiv  Detail & Related papers  (2025-05-29T11:10:41Z)
• Flow-GRPO: Training Flow Matching Models via Online RL [80.62659379624867]
  We propose Flow-GRPO, the first method to integrate online policy reinforcement learning into flow matching models.<n>Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary Differential Equation into an equivalent Differential Equation (SDE) that matches the original model's marginal distribution at all timesteps; and (2) a Denoising Reduction strategy that reduces training denoising steps while retaining the original number of inference steps.
  arXiv  Detail & Related papers  (2025-05-08T17:58:45Z)
• Nesterov Method for Asynchronous Pipeline Parallel Optimization [59.79227116582264]
  We introduce a variant of Nesterov Accelerated Gradient (NAG) for asynchronous optimization in Pipeline Parallelism.<n>Specifically, we modify the look-ahead step in NAG to effectively address the staleness in gradients.<n>We theoretically prove that our approach converges at a sublinear rate in the presence of fixed delay in gradients.
  arXiv  Detail & Related papers  (2025-05-02T08:23:29Z)
• Not-So-Optimal Transport Flows for 3D Point Cloud Generation [58.164908756416615]
  Learning generative models of 3D point clouds is one of the fundamental problems in 3D generative learning.<n>In this paper, we analyze the recently proposed equivariant OT flows that learn permutation invariant generative models for point-based molecular data.<n>We show that our proposed model outperforms prior diffusion- and flow-based approaches on a wide range of unconditional generation and shape completion.
  arXiv  Detail & Related papers  (2025-02-18T02:37:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.