Diffusion Sampling

Follow this topic Ask about this topic

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

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

Noise Schedule Design for Diffusion Models: An Optimal Control Perspective
May 21, 2026Seo Taek Kong, Weina Wang, R. SrikantDiffusion Sampling Diffusion-Based Image Generation
ECE & CSL, University of Illinois Urbana-Champaign · Computer Science Department, Carnegie Mellon University · ECE, CSL & NCSA, University of Illinois Urbana-Champaign
SA-Kura: An Energy-Efficient Systolic Array Accelerator for Locally-Coupled Kuramoto Drift in Diffusion Sampling
May 20, 2026Jeongmin Jin, Kyeongwon Lee, Mundo Jeong +2AI Accelerator Inference Diffusion Sampling
ISLPED '26, Evanston, IL
Goodbye Drift: Anchored Tree Sampling for Long-Horizon Video-to-Video Generation
May 19, 2026Matthew Bendel, Stephen W. Bailey, Mithilesh Vaidya +2Video-Reference Video Generation Long-Horizon Video Generation
Descript, Inc.
Spectral Progressive Diffusion for Efficient Image and Video Generation
May 18, 2026Howard Xiao, Brian Chao, Lior Yariv +1Video Diffusion Models Diffusion Sampling
Stanford University
Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network
May 18, 2026Grigory Bartosh, David Ruhe, Emiel Hoogeboom +3Diffusion Sampling Diffusion-Based Image Generation
*Work done while interning at Google DeepMind Amsterdam, 1University of Amsterdam, 2Google DeepMind Amsterdam · 2Google DeepMind Amsterdam
Wasserstein bounds for denoising diffusion probabilistic models via the Föllmer process
May 18, 2026Yuta KoikeDiffusion Sampling Diffusion Models
*Graduate School of Mathematical Sciences, University of Tokyo · †CREST, Japan Science and Technology Agency
Connections between the Föllmer process and the denoising diffusion probabilistic model
May 18, 2026Yuta KoikeStochastic Differential Equations Diffusion Sampling
*Graduate School of Mathematical Sciences, University of Tokyo · †CREST, Japan Science and Technology Agency
TILT: Model-Intrinsic Reward Alignment For Compositional Diffusion
May 16, 2026Debottam Dutta, Jianchong Chen, Jaehoon Hahm +1Diffusion Model Alignment Diffusion Model Guidance
Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USA · Zhejiang University, China · Physics, University of Illinois Urbana-Champaign, Urbana, IL, USA
Dimension-Uniform Discretization Analysis of Preconditioned Annealed Langevin Dynamics for Multimodal Gaussian Mixtures
May 15, 2026Lorenzo Baldassari, Josselin Garnier, Knut Solna +1Langevin Dynamics Diffusion Sampling
University of Basel · Ecole Polytechnique, IP Paris · University of California Irvine +1
Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?
May 15, 2026Renye Yan, Jikang Cheng, Shikun Sun +7Diffusion Model Alignment Diffusion Sampling
1Peking University · 2Tsinghua University · 3Nanjing University +1
StippleDiffusion: Capacity-Constrained Stippling using Controlled Diffusion
May 15, 2026Ofir Gilad, Aleksander Plocharski, Przemyslaw Musialski +1Constrained Generative Modeling Diffusion Sampling
Ben Gurion University of the Negev, Israel · Warsaw University of Technology, and Akces NCBR, Poland · New Jersey Institute of Technology, United States
Unsupervised 3D Human Pose Estimation via Conditional Multi-view Ancestral Sampling
May 15, 2026Ryohei Goto, Takuya Fujihashi, Shunsuke Saruwatari +1Diffusion Sampling 3D Human Pose Estimation
The University of Osaka
Language Generation as Optimal Control: Closed-Loop Diffusion in Latent Control Space
May 14, 2026ZiYi Dong, Yuliang Huang, Weijian Deng +3Language Model-Based Control Stochastic Optimal Control
Sun Yat-sen University, Guangzhou, Guangdong, China · Australian National University, Canberra, ACT, Australia · Tsinghua University, Beijing, China
Guided Diffusion Sampling for Precipitation Forecast Interventions
May 14, 2026Ayumu Ueyama, Kazuhiko Kawamoto, Hiroshi KeraPrecipitation Forecasting Diffusion Model Guidance
Chiba University · National Institute of Informatics
Training-Free Generative Sampling via Moment-Matched Score Smoothing
May 14, 2026Zhenyu Yao, Daniel PaulinLangevin Dynamics Diffusion Sampling
College of Computing and Data Science Nanyang Technological University
Covariance-aware sampling for Diffusion Models
May 13, 2026Andrea Schioppa, Tim SalimansDiffusion Model Sampling Diffusion Sampling
GDM - Amsterdam · work done at GDM - Amsterdam
Discrete Stochastic Localization for Non-autoregressive Generation
May 13, 2026Yunshu Wu, Jiayi Cheng, Longxuan Yu +4Non-Autoregressive Text Generation Masked Diffusion Models
University of California Riverside · New York University
The critical slowing down in diffusion models
May 12, 2026Luca Maria Del Bono, Giulio Biroli, Patrick Charbonneau +1Diffusion Sampling Critical Slowing Down
Dipartimento di Fisica, Sapienza Università di Roma, Piazzale Aldo Moro 5, Rome 00185, Italy · CNR-Nanotec, Rome unit, Piazzale Aldo Moro 5, Rome 00185, Italy · Laboratoire de Physique Statistique, École normale supérieure, PSL Research University, 24 rue Lhomond, 75005 Paris, France +3
Improving Diffusion Posterior Samplers with Lagged Temporal Corrections for Image Restoration
May 12, 2026Davide Evangelista, Elena Morotti, Francesco Pivi +1Diffusion Sampling Image Restoration
Dept. of Computer Science and Engineering University of Bologna · Dept. of Political and Social Sciences University of Bologna
Is Monotonic Sampling Necessary in Diffusion Models?
May 12, 2026Muhammad Haris KhanDiffusion Sampling Diffusion Timestep Scheduling
Department of Computer Science, University of Copenhagen, Denmark
Couple to Control: Joint Initial Noise Design in Diffusion Models
May 11, 2026Jing Jia, Liyue Shen, Guanyang WangDiffusion Sampling Image Generation
Department of Computer Science Rutgers University Piscataway, NJ 08854 · Department of EECS University of Michigan Ann Arbor, MI 48109 · Department of Statistics Rutgers University Piscataway, NJ 08854
Enforcing Constraints in Generative Sampling via Adaptive Correction Scheduling
May 11, 2026Noah Trupin, Yexiang XueConstrained Generative Modeling Diffusion Sampling
Department of Computer Science, Purdue University
Metropolis-Adjusted Diffusion Models
May 10, 2026Kevin H. Lam, Tyler Farghly, Christopher Williams +3Markov Chain Monte Carlo Diffusion Sampling
Department of Statistics, University of Oxford · Inria, CNRS, École Normale Supérieure, PSL Research University · Department of Mathematical Sciences, University of Copenhagen
Transfer Learning of Multiobjective Indirect Low-Thrust Trajectories Using Diffusion Models and Markov Chain Monte Carlo
May 9, 2026Jannik Graebner, Ryne BeesonMarkov Chain Monte Carlo Trajectory Optimization
PhD Candidate, Department of Mechanical and Aerospace Engineering, Princeton University, NJ, USA. · Assistant Professor, Department of Mechanical and Aerospace Engineering, Princeton University, NJ, USA.
Geometry-Aware Discretization Error of Diffusion Models
May 8, 2026Samuel Hurault, Thomas Moreau, Gabriel PeyréDiffusion Sampling Few-Step Diffusion Sampling
Univ. Gustave Eiffel, CNRS, LIGM · Univ. Paris-Saclay, Inria, CEA · CNRS, ENS, PSL Université
When Diffusion Model Can Ignore Dimension: An Entropy-Based Theory
May 8, 2026Ahmad Aghapour, Erhan BayraktarDiffusion Sampling
Department of Mathematics, University of Michigan, Ann Arbor, 48109
NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models
May 8, 2026Wen Huang, Haoran Sun, Yongjian Guo +8Action-Conditioned Video Generation Action-Conditioned World Models
Tsinghua University · Peking University · JDT AI Infra +1
Stochastic Transition-Map Distillation for Fast Probabilistic Inference
May 8, 2026George Rapakoulias, Peter Garud, Lingjiong Zhu +1Diffusion Model Distillation MeanFlow
Department of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA · Department of Computer Science, Georgia Institute of Technology, Atlanta, GA · Department of Mathematics, Florida State University, Tallahassee, FL
Teacher-Feature Drifting: One-Step Diffusion Distillation with Pretrained Diffusion Representations
May 8, 2026Yuan Zhang, Chenyi Li, Guoqing Ma +7Diffusion Model Distillation Diffusion Sampling
JD Explore Academy, China · The Hong Kong University of Science and Technology · Tsinghua University +1
On the Robustness of Distribution Support under Diffusion Guidance
May 8, 2026Ruijia Cao, Yuchen Wu, Nisha ChandramoorthyDiffusion Guidance Diffusion Sampling
Center for Applied Mathematics, Cornell University · School of Operations Research and Information Engineering, Cornell University · Department of Statistics, The University of Chicago

May 21, 2026J/K move · Enter open · S save

Noise Schedule Design for Diffusion Models: An Optimal Control Perspective

Seo Taek Kong, Weina Wang, R. Srikant

ECE & CSL, University of Illinois Urbana-Champaign · Computer Science Department, Carnegie Mellon University · ECE, CSL & NCSA, University of Illinois Urbana-Champaign

Diffusion Sampling Diffusion-Based Image Generation Diffusion Timestep Scheduling Optimal Control Diffusion Models

Open paper AskPDF arXiv

We develop a principled framework for analyzing and designing noise schedules in diffusion models. We show that one can recast this design problem as an optimal control problem, whose state is the Fisher information of the diffusion process, which evolves according to an ODE, and whose control input is the noise schedule. The objective of the optimal control problem is a functional involving the Fisher information, which is shown to be an upper bound on the Kullback-Leibler sampling error. By solving this optimal control problem, we obtain sufficient conditions on noise schedules under which

\tilde{\mathcal{O}}(d/n)

sampling error is achievable, where

d

is the data dimension and

n

is the number of discretization steps. While existing theoretical works also prove that

\tilde{\mathcal{O}}(d/n)

sampling error bounds are achievable, these results hold for specific noise schedules that differ from those used in practice. Under additional assumptions on the data distribution, we derive a family of noise schedules that recovers the functional forms of schedules widely used in practice. We show that these schedules achieve the

\tilde{\mathcal{O}}(d/n)

error bound when their parameters are chosen according to our analysis. Our theory offers a principled approach to noise schedule design, yielding explicit functional forms and guidance for selecting their parameters.