One-Sided Quantile Coupling for Flow Matching

• URL: http://arxiv.org/abs/2608.00978v1
• Date: Sun, 02 Aug 2026 04:03:59 GMT
• Title: One-Sided Quantile Coupling for Flow Matching
• Abstract summary: 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.
• Score: 8.295726579539016
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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. The coupling that pairs source and target samples strongly affects optimization and sample quality, but structured couplings typically rely on mini-batch transport or assignment procedures whose cost grows at least quadratically in batch size. We propose Quantile Coupling Flow Matching (QC-FM), a lightweight one-sided coupling: rather than matching two pre-sampled batches, it samples only the data batch and constructs each paired source directly. Data ranks projected along a small number of random orthogonal directions are mapped to Gaussian quantiles, and the latent code is completed in the orthogonal complement by conditional Gaussian sampling. The construction is one-dimensional per slice, so the coupling requires no pairwise cost matrix and no assignment to solve. We show that, for each drawn frame, this coupling eliminates the irreducible regression variance along every selected slice and makes the ideal flow exactly straight there, while leaving the sampling prior unchanged: generation still starts from the standard Gaussian, and the training source deviates from it only through the copula of the slice codes, whose transport cost we bound. For training, we apply QC to an anchor subset and complete the remaining source slots with exact Gaussian samples, retaining the QC bias while preserving an explicit signal from the Baseline coupling. Across CIFAR-10, CelebA, FFHQ, and ImageNet-64, 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. These results suggest that preserving projected rank structure is a simple and scalable way to inject useful geometric bias into FM couplings without solving a mini-batch transport problem.

Related papers

• Closed-Form Spectral Regularization for Multi-Task Model Merging [96.82449201305234]
  Model merging combines several independently fine-tuned experts into a single multi-task model without any training data.<n>State-of-the-art merging methods formulate merging as a layer-wise interference problem.<n>We propose SWUDI, a closed-form method that combines a soft exponential filter, which matches the gradient-flow trajectory of iterative descent.
  arXiv  Detail & Related papers  (2026-06-05T14:00:47Z)
• Optimal Transport Flow Matching by Design [26.301026025241374]
  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.
  arXiv  Detail & Related papers  (2026-06-02T18:00:05Z)
• Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schrödinger Samplers [68.9946633641494]
  Flow matching and Schrdinger bridges define probability, yet their inference grids are usually or inherited from one-endpoint diffusion.<n>We derive a conditional-marginal entropy-rate objective for bridge-aware discretization, separating endpoint-conditioned bridge geometry from marginal flow evolution.<n>On EDM/CIFAR-10, the entropic time-discretization gives the best tested five-step FID (186.3 pm 4.0 versus 200.5 pm 2.9 for linear and 238.0 pm 5.3 for cosine)
  arXiv  Detail & Related papers  (2026-05-15T16:11:10Z)
• PrismQuant: Rate-Distortion-Optimal Vector Quantization for Gaussian-Mixture Sources [32.267305083092594]
  We introduce PrismQuant, which transmits the component label losslessly and encodes the residual using the component-matched KLT.<n>Experiments on real-world channel-state-information (CSI) data demonstrate competitive or superior performance compared with transformer-based learned codecs.
  arXiv  Detail & Related papers  (2026-05-15T01:05:28Z)
• 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)
• Posterior Augmented Flow Matching [64.1559809786948]
  Posterior-Augmented Flow Matching (PAFM) is a generalization of flow matching (FM)<n>We show that PAFM improves over FM by up to 3.4 FID50K across different model scales.
  arXiv  Detail & Related papers  (2026-05-01T17:59:59Z)
• 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)
• 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)
• On the Wasserstein Convergence and Straightness of Rectified Flow [54.580605276017096]
  Rectified Flow (RF) is a generative model that aims to learn straight flow trajectories from noise to data.<n>We provide a theoretical analysis of the Wasserstein distance between the sampling distribution of RF and the target distribution.<n>We present general conditions guaranteeing uniqueness and straightness of 1-RF, which is in line with previous empirical findings.
  arXiv  Detail & Related papers  (2024-10-19T02:36:11Z)
• One-Dimensional Deep Image Prior for Curve Fitting of S-Parameters from Electromagnetic Solvers [57.441926088870325]
  Deep Image Prior (DIP) is a technique that optimized the weights of a randomly-d convolutional neural network to fit a signal from noisy or under-determined measurements. Relative to publicly available implementations of Vector Fitting (VF), our method shows superior performance on nearly all test examples.
  arXiv  Detail & Related papers  (2023-06-06T20:28:37Z)

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.