mlsanityData to 14 Oct 2026

Conservative Flows: A New Paradigm of Generative Models

arXiv 2605.06905 ↗First posted 7 May 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Modern generative modeling is dominated by transport from a noise prior to data. We propose an alternative paradigm in which generation is performed by a discrete stochastic dynamics that leaves the data distribution invariant, initialized from data-supported states rather than from noise. The framework can utilize any pretrained flow model. We develop two probability-preserving sampling mechanisms, a corrected Langevin dynamics with a Metropolis adjustment and a predictor-corrector flow, that operate directly on existing checkpoints. We validate the framework on a synthetic Swiss-roll target, ImageNet-256 and Oxford Flowers-102, where our samplers consistently improve over the original generation procedures.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 37 of its 54 references that are in the map. First posted on arXiv 7 May 2026.

Builds on

37 of 54 references.

References · 37

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  9. 2022Scalable Diffusion Models with Transformerscited by 6,054
  10. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  11. 2022Flow Matching for Generative Modelingcited by 5,702
  12. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
25 more
  1. 2018Neural Ordinary Differential Equationscited by 3,779
  2. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  3. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  4. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  5. 2016Density estimation using Real NVPcited by 2,042
  6. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  7. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
  8. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Modelscited by 1,179
  9. 2022Building Normalizing Flows with Stochastic Interpolantscited by 995
  10. 2022Denoising Diffusion Restoration Modelscited by 963
  11. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 939
  12. 2016Conditional Image Generation with PixelCNN Decoderscited by 862
  13. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 703
  14. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 672
  15. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 594
  16. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 583
  17. 2019Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Sufficescited by 227
  18. 2015Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithmcited by 197
  19. 2021Conditional Image Generation with Score-Based Diffusion Modelscited by 197
  20. 2021An Introduction to Deep Generative Modelingcited by 104
  21. 2022Action Matching: Learning Stochastic Dynamics from Samplescited by 98
  22. 2022On Investigating the Conservative Property of Score-Based Generative Modelscited by 16
  23. 2025SoFlow: Solution Flow Models for One-Step Generative Modelingcited by 13
  24. 2023MCMC-Correction of Score-Based Diffusion Models for Model Compositioncited by 7
  25. 2026Manifold-Aware Perturbations for Constrained Generative Modelingcited by 3

Built on by

Not cited yet.