mlsanityData to 13 Oct 2026

Exploring Diffusion and Flow Matching Under Generator Matching

arXiv 2412.11024 ↗First posted 15 Dec 2024cs.LG cs.CVcited by 9

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

Abstract (arXiv)

In this paper, we present a comprehensive theoretical comparison of diffusion and flow matching under the Generator Matching framework. Despite their apparent differences, both diffusion and flow matching can be viewed under the unified framework of Generator Matching. By recasting both diffusion and flow matching under the same generative Markov framework, we provide theoretical insights into why flow matching models can be more robust empirically and how novel model classes can be constructed by mixing deterministic and stochastic components. Our analysis offers a fresh perspective on the relationships between state-of-the-art generative modeling paradigms.

Key facts. Cited by 9 papers in the map (data through 13 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 14 of its 17 references that are in the map. First posted on arXiv 15 Dec 2024.

Builds on

14 of 17 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Flow Matching Guide and Code9 Dec
  2. 2024Generator Matching: Generative modeling with arbitrary Markov processes27 Oct
  3. 2024ANT: Adaptive Noise Schedule for Time Series Diffusion Models18 Oct
  4. 2022Flow Matching for Generative Modeling6 Oct

Other references · 10

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,952
  2. 2020Denoising Diffusion Implicit Modelscited by 9,718
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,028
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,213
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,023
  6. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,023
  7. 2022Building Normalizing Flows with Stochastic Interpolantscited by 979
  8. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 917
  9. 2018Deep Generative Markov State Modelscited by 19
  10. 2024Backstepping for Partial Differential Equations:A Surveycited by 1

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 6; 2026: 3.

9 papers.

  1. 2025Scaling Image and Video Generation via Test-Time Evolutionary Searchcited by 39
  2. 2025Angle Domain Guidance: Latent Diffusion Requires Rotation Rather Than Extrapolationcited by 9
  3. 2025Scale Where It Matters: Training-Free Localized Scaling for Diffusion Modelscited by 6
  4. 2025Warm Starts Accelerate Conditional Diffusioncited by 3
  5. 2026RMFlow: Refined Mean Flow by a Noise-Injection Step for Multimodal Generationcited by 3
  6. 2025A-FloPS: Accelerating Diffusion Models via Adaptive Flow Path Samplercited by 1
  7. 2026Tuning Real-World Image Restoration at Inference: A Test-Time Scaling Paradigm for Flow Matching Modelscited by 1
  8. 2026A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Modelscited by 1
  9. 2025BridgeVoC: Revitalizing Neural Vocoder from a Restoration Perspectivecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025An Introduction to Flow Matching and Diffusion Models
  2. 2025The Generation Phases of Flow Matching: a Denoising Perspective
  3. 2026Latent Process Generator Matching
  4. 2024Explicit Flow Matching: On The Theory of Flow Matching Algorithms with Applications
  5. 2026Simulation-free and finite-time diffusion model
  6. 2026Drift Flow Matching
  7. 2026Notes on generative modeling: flow matching, diffusion, optimal transport and Schr"odinger bridge
  8. 2025Efficiency vs. Fidelity: A Comparative Analysis of Diffusion Probabilistic Models and Flow Matching on Low-Resource Hardware