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. ParaLin++: Accelerating Parallel Diffusion Integrator via Intrinsic Partially Linear Structure

    Oct 22, 2026Jianrong Lu, Zhiyu Zhu, Hui Liu +1Diffusion SamplingDiffusion Model Inference Acceleration

    the Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China · City University of Hong Kong (Dongguan), Dongguan, China · the School of Computing and Information Sciences, Saint Francis University, Hong Kong SAR, China

  2. Density-Level Backward Error for Low-NFE Generative Flows

    Oct 21, 2026Ewsey Obzherin, Valentin KhrulkovDiffusion SamplingDiffusion Model Inference Acceleration

    FusionBrain Lab · MIRIAI

  3. Internal Guidance as a Sampling Method for Tilted Diffusion Models

    Oct 21, 2026Curtis McDonald, Peter BartlettDiffusion Model GuidanceDiffusion Sampling

    Simons Institute, University of California Berkeley · Google DeepMind

  4. Privacy Accounting for Empirical Denoisers

    Oct 20, 2026William Cheng, Dongjun Kim, Mijung ParkDifferential PrivacyDiffusion Sampling

    University of British Columbia · Stanford University · Now at Adobe.

  5. TamedFlow: Trajectory-Aware Distillation for Teacher-Assisted Diffusion Sampling

    Oct 19, 2026Shuaiqi Cheng, Jiahao Zhang, Boyuan Gu +5Diffusion SamplingDiffusion Model Inference Acceleration

    The Hong Kong University of Science and Technology (Guangzhou) · University of Electronic Science and Technology of China · The Hong Kong University of Science and Technology +2

  6. Reflection-Guided Dynamics Rectification for Text-to-Image Generation

    Oct 18, 2026Shuo Xu, Hanrui Ying, Debin Liu +2T2I GenerationT2I Diffusion Models

    Huazhong University of Science and Technology · Sorbonne University · Zhengzhou University

  7. Beyond Pairwise Repulsion: Collective Diversity via Determinant Maximization in Diffusion Sampling

    Oct 15, 2026Kwanyoung Lee, SeungJu Cha, Yebin Ahn +2Diversity-Aware SamplingDiffusion Sampling

    Hanyang University, South Korea

  8. Query-Efficient Rejection Sampling for Parallel Masked Diffusion

    Oct 15, 2026Shiyuan Zhang, Xuheng Li, Qiwei Di +1Parallel Decoding for Diffusion Language ModelsDiffusion Sampling

    Department of Computer Science, University of California, Los Angeles, CA 90095, USA

  9. Score Mismatch and Set-Constrained Sampling in Zero-Shot Conditional Discrete Diffusion

    Oct 15, 2026Renxiang Huang, Yuchen Liang, Yingbin Liang +2Diffusion ModelsDiffusion Sampling

    Department of Electrical and Computer Engineering, University of California, Davis, Davis, CA, 95616, USA · Luddy School of Informatics, Computing, and Engineering, Indiana University Indianapolis, Indianapolis, IN, 46202, USA · Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH, 43210, USA

  10. Asymptotically Exact Negative Guidance of Diffusion Models via Positive-Unlabeled Learning

    Oct 14, 2026Hirohane Takagi, Masashi SugiyamaDiffusion Model GuidanceDiffusion Sampling

    The University of Tokyo, Tokyo, Japan · RIKEN AIP, Tokyo, Japan

  11. Annealed Lévy Diffusion via Gaussian Surrogate Reverse Dynamics

    Oct 14, 2026Yuling Jiao, Lican Kang, Jerry Zhijian Yang +2Diffusion SamplingDiffusion Models

    School of Artificial Intelligence, Wuhan University, Wuhan, Hubei 430072, China. · Institute for Math and AI, Hubei Key Laboratory of Computational Science, and School of Artificial Intelligence, Wuhan University, Wuhan, 430072, China. · School of Mathematics and Statistics, Wuhan University, Wuhan, Hubei 430072, China.

  12. Colored Graph Signal Diffusion Models

    Oct 12, 2026Yiğit Berkay Uslu, Samar Hadou, Shirin Saeedi Bidokhti +1Diffusion ModelsGraph Diffusion

    Dept. of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA

  13. Sampling from Neural Operator Priors to Solve Partial Differential Equations

    Oct 12, 2026Andrew Millard, Joshua Murphy, Zheng ZhaoPDE SolvingPartial Differential Equations

    Department of Computer and Information Science, Linköping University, Sweden. · Department of Political Science, Trinity College Dublin, Ireland.

  14. Imperfect Verifiers, Exact Targets: Inference-Time Scaling for Continuous Generation

    Oct 11, 2026Kijung Jeon, Molei TaoInference-Time GuidanceDiffusion Sampling

    Georgia Institute of Technology

  15. PixARG: Pixel-Asynchronous Retrieval-Augmented Diffusion for Fast and Realistic Image Generation

    Oct 10, 2026Zewei Xin, Qinya Li, Chaoyue Niu +1Image GenerationT2I Diffusion Models

    Shanghai Jiao Tong University, Shanghai, China

  16. TraceSampler: Making Sampling Errors Predictable and Correctable for Accelerated Generative Sampling

    Oct 9, 2026George Matthew, Guoqiang Zhang, Kenta NiwaFew-Step Diffusion SamplingDiffusion Model Inference Acceleration

    University of Exeter, United Kingdom · NTT Communication Science Laboratories, Japan

  17. Finite-Sample Guarantees for Fully Discrete Conditional Diffusion Models

    Oct 9, 2026Qiuyun ZhuConditional Diffusion ModelsDiffusion Sampling

    Department of Statistics and Actuarial Science University of Iowa

  18. TrajCFG: Token-Wise Classifier-Free Guidance via Denoising Trajectory Feedback

    Oct 9, 2026Jingyu Liu, Hao Jiang, Yikang Ding +6Classifier-Free GuidanceDiffusion Sampling

    Renmin University of China · Kling Team, Kuaishou Technology

  19. A Stochastic Analysis Perspective on Diffusion Models

    Oct 9, 2026Stanislas StrasmanScore-Based Generative ModelingDiffusion Sampling

    SU, LPSM · Laboratoire de Probabilités, Statistique et Modélisation, Sorbonne Université

  20. Transformer-Based Masked Diffusion Models Provably Learn Distributions with Latent Structure

    Oct 8, 2026Jingda Wu, Changxiao CaiMasked Diffusion ModelsDiffusion Sampling

    Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, USA.

  21. MAST: Motif-Augmented Diffusion with Search Tree for Spectroscopic Molecular Structure Elucidation

    Oct 8, 2026Chenghao Jia, Mengdi Liu, Hong Chang +2Molecular GenerationDiffusion Sampling

    State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, China · University of Chinese Academy of Sciences, China

  22. Diffusion Removes Langevin's Conditioning Dependence: A Sharp Gaussian Analysis

    Oct 8, 2026Adam Perbost, Francis Bach, Pierre MarionDiffusion SamplingScore-Based Generative Modeling

    Inria, École normale supérieure – PSL Research University Paris, France

  23. Feature Space Adaptation for Effortless Gaussian Process Flows

    Oct 8, 2026Thomas Cowperthwaite, Louis Sharrock, Lachlan Astfalck +1Maximum Marginal Likelihood EstimationGaussian Processes

    University of Cambridge · University College London · University of New South Wales +1

  24. The Lattice of Transition Laws

    Oct 8, 2026T. Y. Tsui, Jiatao Gu, Lingjie LiuParallel DecodingDiffusion Sampling

    University of Pennsylvania

  25. Universal Local Error and Realized Amplification for the First-Order EDM Predictor

    Oct 7, 2026Nicolas Brosse, Arnak S. DalalyanDiffusion Sampling

    CREST, ENSAE Paris, Institut Polytechnique de Paris

  26. How Many Directions Must a Truncated Diffusion Sampler Retain? Matching Bounds Under Power-Law Spectra

    Oct 7, 2026Radmehr Karimian, Ali Mohades, Johannes LedererDiffusion Sampling

    Universit´e de Gen`eve · Universität Hamburg

  27. Lower Bounds for Parallel Diffusion Sampling

    Oct 6, 2026Yiwen Kou, Yimeng WangDiffusion SamplingQuery Complexity

    UCLA

  28. CACFG: Curvature-Aware Classifier-Free Guidance and Optimal Control

    Oct 5, 2026Max Collins, Dasith de Silva Edirimuni, Jordan Vice +2Diffusion Model GuidanceClassifier-Free Guidance

    School of Physics, Maths and Computing The University of Western Australia Perth, WA 6009

  29. Diffusion Transformers are Provably Optimal In-context Generators

    Oct 4, 2026Guoji Fu, Tomoya Wakayama, Ryotaro Kawata +3Diffusion TransformerDiffusion Sampling

    National University of Singapore · RIKEN AIP · The University of Tokyo +1

  30. Hybrid-Basis Feature Forecasting for Diffusion Sampling Acceleration

    Oct 4, 2026Kai-Liang Cheng, Yuan-Yuan Cheng, Yu-fan Jin +1Diffusion SamplingDiffusion Model Caching

    University of Science and Technology of China, China