mlsanityData to 7 Oct 2026

Mean Flows for One-step Generative Modeling

arXiv 2505.13447 ↗First posted 19 May 2025cs.LG cs.CVcited by 524

Not on the map. Why?

Cited by 268 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose a principled and effective framework for one-step generative modeling. We introduce the notion of average velocity to characterize flow fields, in contrast to instantaneous velocity modeled by Flow Matching methods. A well-defined identity between average and instantaneous velocities is derived and used to guide neural network training. Our method, termed the MeanFlow model, is self-contained and requires no pre-training, distillation, or curriculum learning. MeanFlow demonstrates strong empirical performance: it achieves an FID of 3.43 with a single function evaluation (1-NFE) on ImageNet 256x256 trained from scratch, significantly outperforming previous state-of-the-art one-step diffusion/flow models. Our study substantially narrows the gap between one-step diffusion/flow models and their multi-step predecessors, and we hope it will motivate future research to revisit the foundations of these powerful models.

Key facts. Cited by 524 papers in the map (data through 7 Oct 2026). Builds on 43 of its 53 references that are in the map. First posted on arXiv 19 May 2025.

Builds on

43 of 53 references.

References · 43

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  9. 2022Scalable Diffusion Models with Transformerscited by 5,931
  10. 2022Classifier-Free Diffusion Guidancecited by 5,717
  11. 2022Flow Matching for Generative Modelingcited by 5,426
  12. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
31 more
  1. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  2. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  3. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  4. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  6. 2015Variational Inference with Normalizing Flowscited by 2,161
  7. 2023Consistency Modelscited by 1,778
  8. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  9. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  10. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,005
  11. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  12. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
  13. 2023Adversarial Diffusion Distillationcited by 741
  14. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 707
  15. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 666
  16. 2024Autoregressive Image Generation without Vector Quantizationcited by 644
  17. 2024Movie Gen: A Cast of Media Foundation Modelscited by 614
  18. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  19. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  20. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusioncited by 448
  21. 2023Improved Techniques for Training Consistency Modelscited by 430
  22. 2023Simple diffusion: End-to-end diffusion for high resolution imagescited by 413
  23. 2024One Step Diffusion via Shortcut Modelscited by 373
  24. 2024Simplifying, Stabilizing and Scaling Continuous-Time Consistency Modelscited by 276
  25. 2023Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Modelscited by 232
  26. 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generationcited by 211
  27. 2024Consistency Models Made Easycited by 140
  28. 2025Inductive Moment Matchingcited by 107
  29. 2024Consistency Flow Matching: Defining Straight Flows with Velocity Consistencycited by 101
  30. 2024Multistep Consistency Modelscited by 67
  31. 2023One-Step Diffusion Distillation via Deep Equilibrium Modelscited by 60

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 139; 2026: 385.

524 papers.

Sort:

By area:

  1. 2026Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generationcited by 159
  2. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 152
  3. 2025HunyuanImage 3.0 Technical Reportcited by 138
  4. 2025Training Agents Inside of Scalable World Modelscited by 122
  5. 2025Improved Mean Flows: On the Challenges of Fastforward Generative Modelscited by 102
  6. 2026Generative Modeling via Driftingcited by 98
  7. 2025How to build a consistency model: Learning flow maps via self-distillationcited by 96
  8. 2025RELIC: Interactive Video World Model with Long-Horizon Memorycited by 89
  9. 2025Flow Matching Policy Gradientscited by 86
  10. 2025Align Your Flow: Scaling Continuous-Time Flow Map Distillationcited by 81
  11. 2025Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistencycited by 81
  12. 2025What matters for Representation Alignment: Global Information or Spatial Structure?cited by 76
38 more
  1. 2025Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Modelcited by 73
  2. 2025Vid2World: Crafting Video Diffusion Models to Interactive World Modelscited by 67
  3. 2025Diffuse and Disperse: Image Generation with Representation Regularizationcited by 67
  4. 2025A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learningcited by 66
  5. 2026One-step Latent-free Image Generation with Pixel Mean Flowscited by 49
  6. 2025AlphaFlow: Understanding and Improving MeanFlow Modelscited by 40
  7. 2026Categorical Flow Mapscited by 37
  8. 2025Much Ado About Noising: Dispelling the Myths of Generative Robotic Controlcited by 35
  9. 2025Transition Models: Rethinking the Generative Learning Objectivecited by 32
  10. 2026Meta Flow Maps enable scalable reward alignmentcited by 32
  11. 2026Representation Fr'echet Loss for Visual Generationcited by 32
  12. 2026Qwen-Image-2.0 Technical Reportcited by 28
  13. 2026Transition Matching Distillation for Fast Video Generationcited by 27
  14. 2026ELF: Embedded Language Flowscited by 27
  15. 2025SplitMeanFlow: Interval Splitting Consistency in Few-Step Generative Modelingcited by 26
  16. 2026Diamond Maps: Efficient Reward Alignment via Stochastic Flow Mapscited by 26
  17. 2025pi-Flow: Policy-Based Few-Step Generation via Imitation Distillationcited by 25
  18. 2025VITA: Vision-to-Action Flow Matching Policycited by 23
  19. 2026Discrete Flow Mapscited by 23
  20. 2026AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillationcited by 23
  21. 2026Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Modelscited by 23
  22. 2025Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervalscited by 21
  23. 2025From Editor to Dense Geometry Estimatorcited by 20
  24. 2026Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesiscited by 20
  25. 2026FASTER: Rethinking Real-Time Flow VLAscited by 20
  26. 2025Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Samplingcited by 19
  27. 2025One-Step Flow Policy Mirror Descentcited by 18
  28. 2025CMT: Mid-Training for Efficient Learning of Consistency, Mean Flow, and Flow Map Modelscited by 18
  29. 2026One-Step Generative Modeling via Wasserstein Gradient Flowscited by 18
  30. 2025Terminal Velocity Matchingcited by 17
  31. 2025Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Modelscited by 17
  32. 2025TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flowscited by 17
  33. 2026AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discoverycited by 17
  34. 2025Hyperspherical Latents Improve Continuous-Token Autoregressive Generationcited by 16
  35. 2025One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlowcited by 16
  36. 2025Ultra-Fast Language Generation via Discrete Diffusion Divergence Instructcited by 15
  37. 2025Test-time scaling of diffusions with flow mapscited by 15
  38. 2026Action-to-Action Flow Matchingcited by 15

50 most cited of 524 All 524 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching
  2. 2026Look-Ahead and Look-Back Flows: Training-Free Image Generation with Trajectory Smoothing
  3. 2026Self-Consistent Flow: Unifying Velocity and Endpoint Prediction for Rectified Flow Models
  4. 2025An Introduction to Flow Matching and Diffusion Models
  5. 2025A Theoretical Analysis of Discrete Flow Matching Generative Models
  6. 2025From Diffusion to One-Step Generation: A Comparative Study of Flow-Based Models with Application to Image Inpainting
  7. 2025VeCoR -- Velocity Contrastive Regularization for Flow Matching
  8. 2024Flow map matching with stochastic interpolants: A mathematical framework for consistency models