Structured Coupling for Flow Matching

• URL: http://arxiv.org/abs/2605.07676v1
• Date: Fri, 08 May 2026 12:47:37 GMT
• Title: Structured Coupling for Flow Matching
• Abstract summary: We propose a cooperative framework that augments flow matching with structured latent representation learning.<n>By introducing structured latent variables and noise into the source, SCFM jointly learns a structured prior and a continuous transport map.<n>It uses a shared time-dependent recognition network for both latent variable model variational inference and intermediate-time flow velocity estimation.
• Score: 16.361601016656707
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Standard flow matching scales well but typically relies on an unstructured source distribution, limiting its ability to learn interpretable latent structure. Latent-variable models, by contrast, capture structure but often sacrifice generative quality. We bridge this gap by proposing Structured Coupling for Flow Matching (SCFM), a cooperative framework that augments flow matching with structured latent representation learning. By introducing structured latent variables and exogenous noise into the source, SCFM jointly learns a structured prior (via latent variable modeling) and a continuous transport map (via flow matching). It uses a shared time-dependent recognition network for both latent variable model variational inference and intermediate-time flow velocity estimation. This yields a structurally informed yet unconditional, simulation-free flow model, where the latent variable model can also assist flow sampling. Empirically, SCFM facilitates unsupervised latent representation learning for clustering, disentanglement and downstream tasks, while remaining competitive with flow matching in sample quality, showing that meaningful structure can be learned without sacrificing generative fidelity.

Related papers

• Context-weighted Discrete Flow Matching [13.385997589934645]
  We propose a simple modification to the underlying continuous-time Markov chain (CTMC) that incorporates local context information.<n>Our context-weighted sampler improves generation quality with negligible computational overhead.<n>Our scaled cross-entropy loss function reweights the training signal from different tokens and reduces generative perplexity by up to 63% on OpenWebText.
  arXiv  Detail & Related papers  (2026-07-23T15:29:49Z)
• Contrastive-Augmented Flow Matching for Style-Content Disentanglement [26.08049457095161]
  Contrastive Augmented Flow Matching (CAtFM) is a framework that integrates contrastive regularization into an invertible flow matching formulation to promote structured content-style representations.<n>Our experiments operate in the CLIP embedding space, with additional validation using frozen DINO and ALIGN encoders.<n>Overall, CAtFM provides a simple way to couple discriminative constraints with deterministic transport, improving disentanglement and robustness under distribution shift.
  arXiv  Detail & Related papers  (2026-07-14T06:23:52Z)
• Simplifying Flow Matching Transformations with Low-Rank Mixture Models [58.797704398690165]
  We propose using mixtures of probabilistic principal component analyzers (MPPCA) as the latent density for normalizing flows.<n>We simplify the learned flow transformation by learning a latent distribution that more closely aligns with the data distribution in terms of KL divergence.<n>MPPCA models can be fit quickly and cheaply using the expectation-maximization algorithm, making them a practical choice for initializing latent distributions even in high-dimensional generative tasks.
  arXiv  Detail & Related papers  (2026-06-29T03:03:06Z)
• Topological Flow Matching [56.16372813551555]
  Flow matching is a powerful generative modeling framework, valued for its simplicity and strong empirical performance.<n>We introduce topological flow matching, a topology-aware generalization of flow matching.<n>We demonstrate its effectiveness on diverse structured datasets, including brain fMRIs, ocean currents, seismic events, and traffic flows.
  arXiv  Detail & Related papers  (2026-06-14T16:29:33Z)
• Cross-Sample Relational Fusion: Unifying Domain Generalization and Class-Incremental Learning [83.67663266193308]
  Class-Incremental Learning (CIL) requires a learning system to learn new classes while retaining previously learned knowledge.<n>In real-world scenarios such as autonomous driving, a system trained on urban roads in sunny weather may later need to operate in rural or highway environments.<n>We propose a unified framework to address domain shift and catastrophic forgetting simultaneously.
  arXiv  Detail & Related papers  (2026-05-09T09:49:13Z)
• Semi-structured multi-state delinquency model for mortgage default [7.0177704222466994]
  We propose a semi-structured discrete-time multi-state model to analyse mortgage delinquency transitions.<n>This model combines an easy-to-understand structured additive predictor, with a flexible neural network component that captures complex nonlinearities and higher-order interactions.
  arXiv  Detail & Related papers  (2026-03-27T11:22:22Z)
• GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis [54.39598154430305]
  We propose a Data-to-Data Flow Matching framework that learns deterministic transformations directly between paired views.<n>PDG-FM constrains flow trajectories using geodesic interpolants derived from probability density metrics of pretrained diffusion models.<n>These results highlight the advantages of incorporating data-dependent geometric regularization into deterministic flow matching for consistent novel view generation.
  arXiv  Detail & Related papers  (2026-03-01T09:30:11Z)
• Fractal Flow: Hierarchical and Interpretable Normalizing Flow via Topic Modeling and Recursive Strategy [3.648417123399582]
  We propose Fractal Flow, a novel normalizing flow architecture that enhances both expressiveness and interpretability.<n> Experiments on MNIST, FashionMNIST, CIFAR-10, and geophysical data demonstrate that the Fractal Flow achieves latent clustering, controllable generation, and superior estimation accuracy.
  arXiv  Detail & Related papers  (2025-08-27T10:25:15Z)
• Unfolding Generative Flows with Koopman Operators: Fast and Interpretable Sampling [25.420559502119485]
  Continuous Normalizing Flows (CNFs) enable elegant generative modeling but remain bottlenecked by slow sampling.<n>Recent approaches such as Rectified Flow and OT-CFM accelerate sampling by straightening trajectories, yet the learned dynamics remain nonlinear black boxes.<n>We propose globally linearizing flow dynamics via Koopman theory.
  arXiv  Detail & Related papers  (2025-06-27T15:16:16Z)
• Probabilistic Forecasting via Autoregressive Flow Matching [1.5467259918426441]
  FlowTime is a generative model for probabilistic forecasting of timeseries data.<n>We decompose the joint distribution of future observations into a sequence of conditional densities, each modeled via a shared flow.<n>We demonstrate the effectiveness of FlowTime on multiple dynamical systems and real-world forecasting tasks.
  arXiv  Detail & Related papers  (2025-03-13T13:54:24Z)
• Time-series Generation by Contrastive Imitation [87.51882102248395]
  We study a generative framework that seeks to combine the strengths of both: Motivated by a moment-matching objective to mitigate compounding error, we optimize a local (but forward-looking) transition policy. At inference, the learned policy serves as the generator for iterative sampling, and the learned energy serves as a trajectory-level measure for evaluating sample quality.
  arXiv  Detail & Related papers  (2023-11-02T16:45:25Z)
• GFlowNet-EM for learning compositional latent variable models [115.96660869630227]
  A key tradeoff in modeling the posteriors over latents is between expressivity and tractable optimization. We propose the use of GFlowNets, algorithms for sampling from an unnormalized density. By training GFlowNets to sample from the posterior over latents, we take advantage of their strengths as amortized variational algorithms.
  arXiv  Detail & Related papers  (2023-02-13T18:24:21Z)
• SIReN-VAE: Leveraging Flows and Amortized Inference for Bayesian Networks [2.8597160727750564]
  This work explores incorporating arbitrary dependency structures, as specified by Bayesian networks, into VAEs. This is achieved by extending both the prior and inference network with graphical residual flows. We compare our model's performance on several synthetic datasets and show its potential in data-sparse settings.
  arXiv  Detail & Related papers  (2022-04-23T10:31:08Z)
• Bayesian Structure Learning with Generative Flow Networks [85.84396514570373]
  In Bayesian structure learning, we are interested in inferring a distribution over the directed acyclic graph (DAG) from data. Recently, a class of probabilistic models, called Generative Flow Networks (GFlowNets), have been introduced as a general framework for generative modeling. We show that our approach, called DAG-GFlowNet, provides an accurate approximation of the posterior over DAGs.
  arXiv  Detail & Related papers  (2022-02-28T15:53:10Z)
• Out-of-distribution Generalization via Partial Feature Decorrelation [72.96261704851683]
  We present a novel Partial Feature Decorrelation Learning (PFDL) algorithm, which jointly optimize a feature decomposition network and the target image classification model. The experiments on real-world datasets demonstrate that our method can improve the backbone model's accuracy on OOD image classification datasets.
  arXiv  Detail & Related papers  (2020-07-30T05:48:48Z)

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.