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. FASA: Feedback-Aware Sampling Adaptation for Efficient Diffusion-Based VLA Models

    Sep 16, 2026Yuchen Han, Jianhan Wu, Xiaoyang Qu +3Diffusion SamplingEfficient VLA Model Inference

    South China University of Technology Guangzhou, China · Ping An Technology (Shenzhen) Co., Ltd. Shenzhen, China · Harbin Institute of Technology Shenzhen, China

  2. Spatially Adaptive Noise Injection

    Sep 16, 2026Frantzeska Lavda, Maciej Falkiewicz, Van Khoa Nguyen +1Diffusion SamplingDiffusion-Based Image Generation

    University of Applied Sciences Western Switzerland, HES-SO Geneva · Computer Science Department, University of Geneva

  3. METALICA: METAdynamics and repLICA exchange for enhanced diffusion sampling

    Sep 15, 2026Alireza Omidi, Jiajun He, Jörg Gsponer +1Diffusion Sampling

    University of British Columbia · University of Cambridge

  4. Accelerating Diffusion Sampling via Speculative Draft Trees

    Sep 15, 2026Marcello Bullo, Yanxiao Liu, Öykü Sıla Güner +2Diffusion SamplingDiffusion Model Acceleration

    Imperial College London

  5. Score-based Outlier Generation via Controlling the Radon-Nikodym Derivative

    Sep 10, 2026Amartya Mukherjee, Tristan Milne, Kry Yik-Chau Lui +2Diffusion SamplingSynthetic Anomaly Generation

    Department of Applied Mathematics, University of Waterloo, Waterloo, Ontario, Canada N2L 3G1 · Royal Bank of Canada, 1 Place Ville Marie, Montreal, Quebec, H3C 3A9

  6. Deep operator learning for efficient sampling from invariant measures of stochastic differential equations

    Sep 10, 2026Ling Guo, Lei Li, Jingtong ZhangStochastic Differential EquationsDiffusion Sampling

    Department of Mathematics, Shanghai Normal University, Shanghai, China · School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai, China · Institute of Natural Sciences, MOE-LSC, Shanghai Jiao Tong University, Shanghai, China

  7. Let It Go or Learn to Self-Correct: Continuous Diffusion for Constrained Discrete Tasks

    Sep 8, 2026Mariia Drozdova, Stéphane Liem Nguyen, François FleuretConstrained Generative ModelingDiffusion Sampling

    University of Geneva

  8. Transformers as In-Context Samplers: From Closed-Form Diffusion to Estimation-Free Sampling

    Sep 8, 2026Arman Adibi, Alireza Jafari, Mohammad Ghavamzadeh +1TransformerDiffusion Sampling

    School of Computer and Cyber Sciences, Augusta University · Department of Computer Science, University of Virginia · Qualcomm AI Research

  9. LATS: Levy Adaptive Tree Sampling for Feedback-Driven Diverse Target Discovery

    Sep 6, 2026Binglin Ji, Anindya Sarkar, Hengchang Lu +3Adaptive SamplingDiffusion Sampling

    Department of CSE, Washington University in St.Louis, USA

  10. SwiftExplorer: Training-free Diffusion Model Alignment with Swift Diversity Exploration

    Sep 6, 2026Renye Yan, Jikang Cheng, You Wu +5Diffusion Model AlignmentDiffusion Model Guidance

    Peking University Beijing, China · Nanjing University Nanjing, China · Huazhong Agricultural University Wuhan, China +1

  11. From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion

    Sep 1, 2026Satoshi HayakawaDiffusion SamplingDiffusion Language Model Decoding

    The University of Tokyo

  12. ASSERT: Adaptive Stochastic Sampling for Robust Diffusion Models on Analog Compute-in-Memory Hardware

    Sep 1, 2026Yuannuo Feng, Yizhe Chen, Wenshuai Yao +4Compute-in-MemoryDiffusion Sampling

    School of Integrated Circuit Science and Engineering, Beihang University, Beijing, China · Zhicun Research Lab, Beijing, China · School of Integrated Circuits, Peking University, Beijing, China +1

  13. DiffSAC: Diffusion-guided Sampling for Consensus-based Robust Estimation

    Aug 31, 2026Chang Nie, Guangming Wang, Zhe Liu +1Diffusion SamplingRobust Estimation

    School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, 200240, China. · 2Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai, 200240, China. · Department of Engineering, Cambridge University, Cambridge, CB2 1TN, UK.

  14. The information geometry of product-reference discrete diffusion: Interaction growth complexity and optimal scheduling

    Aug 28, 2026Martin J. WainwrightDiffusion SamplingDiffusion Timestep Scheduling

    Lab for Information and Decision Systems Statistics and Data Science Center EECS and Mathematics, Massachusetts Institute of Technology

  15. Self-Augmented Diffusion Guidance for Physics-Informed Generation

    Aug 27, 2026Akira Osaka, Naoya Takeishi, Takehisa YairiPhysics-Informed Diffusion ModelsPhysics-Informed Generative Modeling

    School of Engineering The University of Tokyo

  16. StocBench: A Benchmark for Generative Modeling of Stochastic Dynamics

    Aug 23, 2026Sebastian Pfister, Benjamin Holzschuh, Nils ThuereyGenerative ModelingProbabilistic Forecasting

    School of Computation, Information and Technology, Technical University of Munich, Germany.

  17. When Denoising Hurts: Rethinking the Terminal Step of Diffusion Time Series Forecasters -- Extended Version

    Aug 14, 2026Dat Nguyen-Cong, Luong Tran, Tung KieuTime Series ForecastingDiffusion Sampling

    FPT Software AI Center, FPT Corporation · Department of Computer Science, Aalborg University, Denmark

  18. The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity

    Aug 13, 2026Martin J. WainwrightMasked Diffusion ModelsDiffusion Sampling

    Lab for Information and Decision Systems · Statistics and Data Science Center · EECS and Mathematics

  19. Simplex Relaxation for Discrete Diffusion

    Aug 11, 2026Jinya Sakurai, Patrick Pynadath, Satoshi Hayakawa +4Diffusion SamplingDiffusion Language Models

    1NTU Singapore · 2The University of Tokyo · Institute for Advanced Intelligence and Computing (IAIC), A*STAR +2

  20. Tokenizer-Generator Coupling in Medical Image Generation

    Aug 7, 2026Liam ChalcroftImage TokenizationDiffusion Sampling

    University College London London, United Kingdom

  21. Local Epistemic Uncertainty Guided Active Sampling for Plug-and-play Diffusive Image Restoration

    Aug 7, 2026Jiaqi Zhang, Zheng Pang, Rongrong Gao +2Diffusion Models for Image RestorationDiffusion Model Guidance

    Jiangsu University, Zhenjiang, China · Xi’an University of Technology, Xi’an, China

  22. PAST: Prompt-Adaptive Sampling Termination for Efficient Diffusion Model

    Aug 7, 2026Renye Yan, Jikang Cheng, You Wu +4Intrinsic Reward MethodsReinforcement Learning

    Peking University Beijing, China

  23. HyperbolicDiffusion: Sharp & Scalable Tiled Generation on the Hyperbolic Plane

    Aug 4, 2026Hugo Caselles-DupréDiffusion SamplingImage Generation

    Obvious Research Paris, France

  24. Disagree to Accelerate: Closing the Loop on Diffusion Feature Forecasts

    Aug 3, 2026Yanchao Li, Jiaqing Xie, Ben Gao +6Diffusion SamplingDiffusion Model Caching

    1Nanjing University · 2Shanghai Artificial Intelligence Laboratory · 3North University of China +2

  25. Improving scDiffusion with Sparsity-Biased Classifier-Free Guidance

    Jul 31, 2026Yu Song, Hao Sun, Ikuko Nishikawa +1Classifier-Free GuidanceDiffusion Sampling

    College of Information Science and Engineering, Ritsumeikan University, Osaka, Japan

  26. FairDiffuseVQVAE: Sampling-Time Fairness in Tabular Diffusion via Conditional Refinement of Vector-Quantized Latents

    Jul 31, 2026Nitish Nagesh, Mahdi Bagheri, Amir M. RahmaniAlgorithmic FairnessDiffusion Sampling

    University of California, Irvine

  27. Conditioning Tree-Based Diffusions and Flows for Probabilistic Tabular Regression

    Jul 30, 2026Silas KoemenFlow MatchingGradient-Boosted Decision Trees

    Independent Researcher

  28. When Do Learned Diffusion Proposals Help Constraint Solving? A Controlled Study on Continuous Algebraic Systems

    Jul 29, 2026Quang Bui, Sparsh Roy, Akash Gundimeda +1Graph Neural NetworksDiffusion Sampling

    1SAID Lab · 2American International School Vienna · 3Hopewell Valley Central High School +2

  29. Flow Map Learning via Nongradient Vector Flow

    Jul 29, 2026Mark Goldstein, Anshuk Uppal, Raghav Singhal +2Diffusion SamplingFlow Map Learning

    Center for Computational Mathematics, Flatiron Institute. · Department of Applied Mathematics and Computer Science, Technical University of Denmark. · Courant Institute, New York University.

  30. Denoising growth complexity: Data geometry and certified schedules for diffusion sampling

    Jul 28, 2026Martin J. WainwrightSample ComplexityDiffusion Sampling

    Lab for Information and Decision Systems Statistics and Data Science Center EECS and Mathematics, Massachusetts Institute of Technology