mlsanityData to 7 Oct 2026

RMFlow: Refined Mean Flow by a Noise-Injection Step for Multimodal Generation

arXiv 2602.00849 ↗First posted 31 Jan 2026cs.LG cs.AI cs.NAcited by 3

Not on the map. Why?

Abstract (arXiv)

Mean flow (MeanFlow) enables efficient, high-fidelity image generation, yet its single-function evaluation (1-NFE) generation often cannot yield compelling results. We address this issue by introducing RMFlow, an efficient multimodal generative model that integrates a coarse 1-NFE MeanFlow transport with a subsequent tailored noise-injection refinement step. RMFlow approximates the average velocity of the flow path using a neural network trained with a new loss function that balances minimizing the Wasserstein distance between probability paths and maximizing sample likelihood. RMFlow achieves near state-of-the-art results on text-to-image, context-to-molecule, and time-series generation using only 1-NFE, at a computational cost comparable to the baseline MeanFlows.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 52 of its 63 references that are in the map. First posted on arXiv 31 Jan 2026.

Builds on

52 of 63 references.

References · 52

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2022Flow Matching for Generative Modelingcited by 5,426
  7. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  8. 2018Neural Ordinary Differential Equationscited by 3,733
  9. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  10. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  11. 2023Consistency Modelscited by 1,778
  12. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,447
38 more
  1. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  2. 2014Deep Visual-Semantic Alignments for Generating Image Descriptionscited by 966
  3. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
  4. 2023Training Diffusion Models with Reinforcement Learningcited by 939
  5. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 897
  6. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  7. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 734
  8. 2022On Distillation of Guided Diffusion Modelscited by 721
  9. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 707
  10. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 670
  11. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 666
  12. 2024Movie Gen: A Cast of Media Foundation Modelscited by 614
  13. 2025Mean Flows for One-step Generative Modelingcited by 524
  14. 2023Improved Techniques for Training Consistency Modelscited by 430
  15. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  16. 2024Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Designcited by 294
  17. 2024Simplifying, Stabilizing and Scaling Continuous-Time Consistency Modelscited by 276
  18. 2019Cormorant: Covariant Molecular Neural Networkscited by 262
  19. 2023StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesiscited by 212
  20. 2023Geometric Latent Diffusion Models for 3D Molecule Generationcited by 185
  21. 2021E(n) Equivariant Normalizing Flowscited by 165
  22. 2023UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANscited by 165
  23. 2024Consistency Models Made Easycited by 140
  24. 2021LAFITE: Towards Language-Free Training for Text-to-Image Generationcited by 126
  25. 2024AlphaFold Meets Flow Matching for Generating Protein Ensemblescited by 105
  26. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 104
  27. 2025How to build a consistency model: Learning flow maps via self-distillationcited by 96
  28. 2022Maximum Likelihood Training for Score-Based Diffusion ODEs by High-Order Denoising Score Matchingcited by 79
  29. 2023One-Step Diffusion Distillation via Deep Equilibrium Modelscited by 60
  30. 2019Flood Prediction Using Machine Learning Models: Literature Reviewcited by 36
  31. 2022FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equationcited by 36
  32. 2021High-Resolution Complex Scene Synthesis with Transformerscited by 31
  33. 2025FlowTok: Flowing Seamlessly Across Text and Image Tokenscited by 31
  34. 2023User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systemscited by 30
  35. 2024Flow matching achieves almost minimax optimal convergencecited by 27
  36. 2025Diff2Flow: Training Flow Matching Models via Diffusion Model Alignmentcited by 27
  37. 2024Unified Generative Modeling of 3D Molecules via Bayesian Flow Networkscited by 18
  38. 2024Exploring Diffusion and Flow Matching Under Generator Matchingcited by 9

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Second Order Drifting Modelscited by 1
  2. 2026HybridFlow: A 2-NFE Generative Policy for Real-Time Robotic Manipulationcited by 0
  3. 2026Diffusion Image Generation with Explicit Modeling of Data Manifold Geometrycited by 0