Diffusion Sampling

Ask about this topic

Overview

Diffusion sampling starts with noise and repeatedly denoises it to generate data, using reverse stochastic processes such as DDPM or deterministic flows such as DDIM and probability-flow ODEs. Work improves this process with higher-order or adaptive solvers, learned timestep schedules, and methods that reuse or predict model computations; discrete and masked diffusion models also require choices about which tokens to reveal and when. Guidance, particle methods, and search can steer samples toward rewards, constraints, diversity, or solutions to inverse problems, with applications spanning image and text generation, molecules, and scientific modeling. A central tension is reducing steps and computation without losing fidelity, diversity, or correctness, while theory seeks sharper guarantees for error, stability, and sampling cost.

Latest papers

CardsList

264 papers49 papers in the last four weeks, up 104% on the four weeks before. 0.3% of all new papers.

  1. Spectral Prior for Reducing Exposure Bias in Diffusion Models

    Jul 24, 2026Yuya Kobayashi, Masato Ishii, Yuhta Takida +2Diffusion Model GuidanceDiffusion Sampling

    Sony AI · Sony Group Corporation

  2. Inference-Time Scaling of Diffusion Models via Progressive Seed Pruning

    Jul 23, 2026Rogerio Guimaraes, Pietro PeronaDiffusion Model SamplingDiffusion Sampling

    California Institute of Technology, Pasadena CA 91125, USA

  3. Analytic Distribution of Classifier-Free Guidance for Schedule Design

    Jul 22, 2026Enze Jiang, Zheng MaClassifier-Free GuidanceDiffusion Sampling

    School of Mathematical Sciences Shanghai Jiao Tong University Shanghai, China

  4. Provable diffusion-based posterior sampling for linear inverse problems via DDIM

    Jul 21, 2026Yuchen Jiao, Na Li, Changxiao Cai +2Diffusion Models for Image RestorationBayesian Inverse Problems

    Department of Statistics and Data Science, Chinese University of Hong Kong, Hong Kong · Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, USA · Department of Statistics and Data Science, the Wharton School, University of Pennsylvania, PA, USA

  5. DiFA: Inference-Time Forward-Process Alignment for Diffusion Models

    Jul 20, 2026Shigui Li, Delu ZengDiffusion Model AlignmentDiffusion Sampling

    School of Mathematics, South China University of Technology, Guangzhou, China · School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China

  6. Integration Matters: Rollout-Based Training for Constrained Diffusion Models

    Jul 15, 2026Xiaoxuan Liang, Saeid Naderiparizi, Berend Zwartsenberg +1Constrained Generative ModelingDiffusion Sampling

    University of British Columbia · Inverted AI · Alberta Machine Intelligence Institute

  7. Diversify Diffusion with Temperature Sampling and Variance-Corrective Time Shifting

    Jul 12, 2026Peizhuo Li, Emre Aksan, Alexandru-Eugen Ichim +2Diffusion Sampling

    ETH Zurich · Google

  8. Score Accuracy Along the Forward Diffusion Does Not Certify Numerical Stability in Diffusion Sampling

    Jul 9, 2026Yiwei ZhouScore MatchingDiffusion Sampling

  9. Guidance Breaks the Fitted Operator: A Terminal-Fitted Repair for Classifier-Free Guidance

    Jul 8, 2026Shiheng ZhangClassifier-Free GuidanceDiffusion Sampling

    University of Washington

  10. Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling

    Jul 7, 2026Robert Gruhlke, Julius Berner, David Sommer +1Stochastic Differential EquationsDiffusion Sampling

    Freie Universität Berlin · NVIDIA · WIAS +2

  11. Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editing

    Jul 7, 2026Wanglong Lu, Lingming Su, Kaijie Shi +4Latent Diffusion ModelsDiffusion Sampling

    College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325035, China · Department of Computer Science, Memorial University of Newfoundland, St. John’s, NL A1B 3X5, Canada · AI Analytics Team, Nasdaq, St. John’s, NL A1A 0L9, Canada +2

  12. x-Prediction Is All You Need:Training-Free Accelerated Generation via Endpoint Decodability

    Jul 7, 2026Xin Peng, Ang GaoDiffusion SamplingFew-Step Diffusion Sampling

    School of Physical Science and Technology, Beijing University of Posts and Telecommunications, Beijing, China

  13. D2PO: Optimizing Diffusion Samplers via Dynamic Preference

    Jul 7, 2026Jinkyu Kim, Jinyoung Choi, Bohyung HanDiffusion Model AlignmentDirect Preference Optimization

    1ECE & 2IPAI, Seoul National University, Korea · 3AIGS, Ulsan National Institute of Science and Technology, Korea

  14. Non-Asymptotic Error Bounds for SMC with Biased Proposals: Application to Conditional Diffusion Sampling

    Jul 6, 2026Stanislas Strasman, Gabriel Victorino Cardoso, Sylvain Le Corff +2Markov Chain Monte CarloMarkov Models

    SU, LPSM · Sorbonne Université and Université Paris Cité, CNRS, LPSM, F-75005 Paris, France · LPSM +2

  15. Asymptotic Preservation and Uniform Accuracy of Diffusion and Flow-Matching Samplers

    Jul 5, 2026Shiheng ZhangFlow MatchingDiffusion Sampling

    University of Washington

  16. Adaptive Reparametrized Time for Score-Based Diffusion Sampling

    Jul 2, 2026Yilie Huang, Wenpin Tang, Xun Yu ZhouDiffusion SamplingAdaptive Sampling

    Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong. · Department of Industrial Engineering and Operations Research, Columbia University, New York, NY 10027, USA. · Department of Industrial Engineering and Operations Research and Data Science Institute, Columbia University, New York, NY 10027, USA.

  17. A Mathematical Introduction to Diffusion Models

    Jul 2, 2026Jianfeng LuDiffusion SamplingDiffusion Models

  18. Accelerating Discrete Diffusion Models with Parallel-In-Time Sampling

    Jul 1, 2026Yu Yao, Huanjian Zhou, Andi Han +2Diffusion SamplingDiffusion Model Inference Acceleration

    The University of Tokyo · The University of Sydney · RIKEN AIP & The Institute of Statistical Mathematics +1

  19. Accelerated Likelihood Maximization for Diffusion-based Versatile Content Generation

    Jun 30, 2026Hyunsoo Lee, Inwoo Hwang, Young Min KimDiffusion SamplingDiffusion Model Acceleration

    ECE, Seoul National University · INMC & IPAI, Seoul National University

  20. OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models

    Jun 30, 2026Huanlin Gao, Fang Zhao, Qiang Hui +8Diffusion SamplingDiffusion Model Caching

    Data Science & Artificial Intelligence Research Institute, China Unicom · Unicom Data Intelligence, China Unicom · National Key Laboratory for Novel Software Technology, Nanjing University

  21. Diffusion-warm sampling of the XY model enables fast thermalization at scale

    Jun 29, 2026Sehmimul Hoque, Roger Melko, Pooya RonaghMarkov Chain Monte CarloDiffusion Sampling

    Institute for Quantum Computing, University of Waterloo, Waterloo, Ontario N2L 3G1, Canada · Department of Physics and Astronomy, University of Waterloo, Waterloo, Ontario N2L 3G1, Canada · Perimeter Institute for Theoretical Physics, Waterloo, Ontario N2L 2Y5, Canada +1

  22. VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing

    Jun 26, 2026Kijung Jeon, Thuy-Duong Vuong, Molei TaoConstrained Generative ModelingMasked Diffusion Models

    Georgia Tech · UCSD

  23. Sampling the Schwinger Model with Gauge-Equivariant Diffusion

    Jun 25, 2026Octavio Vega, Aida X. El-KhadraDiffusion SamplingGenerative Modeling

    Department of Physics University of Illinois Urbana-Champaign Urbana, IL 61801

  24. ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration

    Jun 25, 2026Qicheng Zhao, Yu Li, Qi Sun +1Diffusion TransformerDiffusion Sampling

    Zhejiang University, Hangzhou, China

  25. Retrieval-Warmed Energy-Based Reasoning: A Five-Arm Ablation Methodology for Diffusion-as-Inference on Structured Reasoning Tasks

    Jun 25, 2026Libo Sun, Po-Wei Harn, Zewei Zhang +2Diffusion SamplingEnergy-Based Models

    Department of Computer Science and Software Engineering, Auburn University, Auburn, AL 36830, USA · Department of Information Management, National Central University, Taoyuan 320317, Taiwan

  26. Grounding Generative Policies in Physics: Optimization-Guided Diffusion for Robot Control

    Jun 23, 2026Sabrina Bodmer, René Zurbrügg, Tifanny Portela +5Diffusion Model GuidanceRobotic Grasping

    ETH Zurich · EPFL

  27. Diffusion Models Adapt to Low-Dimensional Structure Under Flexible Coefficient Choices

    Jun 22, 2026Changxiao Cai, Yuchen Jiao, Gen LiDiffusion Model SamplingDiffusion Sampling

    Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, USA · Department of Statistics and Data Science, Chinese University of Hong Kong, Hong Kong

  28. Walk fast but be careful: Understanding Parallel Sampling in Masked Diffusion

    Jun 22, 2026Vansh Bansal, Cholyeon Cho, Syamantak Kumar +2Masked Diffusion ModelsDiffusion Sampling

    UT Austin SDS · UT Austin CS · UT Austin ECE

  29. Variance-Tilted Diffusion Models for Diverse Sampling

    Jun 20, 2026Iskander Azangulov, Leo Zhang, Kianoosh AshouritaklimiDoob H-TransformDiffusion Model Sampling

    Department of Statistics, University of Oxford, Oxford, UK.

  30. Volterra Generative Models

    Jun 16, 2026Yusen Jia, Bingyan HanDiffusion SamplingDiffusion-Based Image Generation

    The Hong Kong University of Science and Technology (Guangzhou)