mlsanityData to 14 Oct 2026

Low-Pass Flow Matching

arXiv 2606.02177 ↗First posted 1 Jun 2026cs.LGcited by 0

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Flow Matching typically relies on white noise sources, a choice often misaligned with the power spectra of natural data, which tend to decay with frequency. To address this, we introduce Low-Pass Flow Matching, a variant of Flow Matching based on an operator-modulated interpolant. This formulation induces a time-varying spectral bias that transitions from the source spectrum to a frequency-decaying bias as the path approaches the data. We validate our method on unconditional image generation tasks, including the scientific Galaxy10 dataset. Empirically, we show that our method is particularly effective when paired with adaptive ODE solvers, where it improves or preserves sample quality while substantially reducing sampling cost compared to standard baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 34 of its 53 references that are in the map. First posted on arXiv 1 Jun 2026.

Builds on

34 of 53 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025FourierFlow: Frequency-aware Flow Matching for Generative Turbulence Modeling1 Jun
  2. 2025How to build a consistency model: Learning flow maps via self-distillation24 May
  3. 2023SE(3)-Stochastic Flow Matching for Protein Backbone Generation3 Oct
  4. 2023PFGM++: Unlocking the Potential of Physics-Inspired Generative Models8 Feb
  5. 2023Improving and generalizing flow-based generative models with minibatch optimal transport1 Feb
  6. 2022Flow Matching for Generative Modeling6 Oct
  7. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow7 Sep
  8. 2022Equivariant Diffusion for Molecule Generation in 3D31 Mar

Other references · 26

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2022Building Normalizing Flows with Stochastic Interpolantscited by 995
  7. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 599
  8. 2023Photorealistic Video Generation with Diffusion Modelscited by 306
  9. 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 250
  10. 2023FreeU: Free Lunch in Diffusion U-Netcited by 196
  11. 2022Generative Modelling With Inverse Heat Dissipationcited by 167
  12. 2021E(n) Equivariant Normalizing Flowscited by 165
14 more
  1. 2022Diffusion Probabilistic Model Made Slimcited by 121
  2. 2022Poisson Flow Generative Modelscited by 95
  3. 2021Learning to See by Looking at Noisecited by 92
  4. 2022Blurring Diffusion Modelscited by 91
  5. 2025The Principles of Diffusion Modelscited by 76
  6. 2025A Fourier Space Perspective on Diffusion Modelscited by 52
  7. 2024Time Series Diffusion in the Frequency Domaincited by 37
  8. 2024Blue noise for diffusion modelscited by 29
  9. 2022Spectral Diffusion Processescited by 25
  10. 2023GenPhys: From Physical Processes to Generative Modelscited by 19
  11. 2023Frequency Compensated Diffusion Model for Real-scene Dehazingcited by 17
  12. 2025Spectral Analysis of Diffusion Models with Application to Schedule Designcited by 13
  13. 2025Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Controlcited by 11
  14. 2024GUD: Generation with Unified Diffusioncited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026InjectFlow: Weak Guides Strong via Orthogonal Injection for Flow Matching
  2. 2026Flow Matching is Adaptive to Manifold Structures
  3. 2026FlowBudget: Training-Free Sampling-Budget Estimation for Flow Matching Models
  4. 2026Training-Free Refinement of Flow Matching with Divergence-based Sampling
  5. 2026SpectralDiT: Timestep-Conditioned Spectral Residual Correction for Flow-Matching DiTs
  6. 2026The Velocity Deficit: Initial Energy Injection for Flow Matching
  7. 2026Noise-Robust Conditional Flow Matching: Generating Clean Samples from Noisy Datasets
  8. 2025Scale-Adaptive Generative Flows for Multiscale Scientific Data