Diffusion Model Sampling

Follow this topic Ask about this topic

Diffusion model sampling turns a trained model’s noisy predictions into data by approximating a reverse-time stochastic process or probability-flow ODE. Common approaches include DDIM and higher-order ODE solvers, adaptive timestep schedules, covariance-aware updates, and parallel or adaptive unmasking for discrete text models. Guidance, sequential Monte Carlo, and constrained or reward-aware sampling steer generations toward desired properties, while convergence analyses and image, text, molecular, and physical benchmarks assess accuracy and cost. A central tension is reducing steps and computation without amplifying score-model error, losing diversity, or sacrificing fidelity to constraints and rewards.

Latest papers

82 papers14 papers in the last four weeks, up 180% on the four weeks before. 0.1% of all new papers.

An ODE-based Sampler for Discrete Diffusion Models
Oct 29, 2026Samson Gourevitch, Yazid Janati, Eric Moulines +3Diffusion Model Sampling Diffusion Models
CMAP, Ecole polytechnique · Institute of Foundation Models · MBZUAI +2
Composing and Steering Diffusion Models with Generalized Feynman-Kac Correctors
Oct 29, 2026Wael Mattar, Daniel FreedmanDiffusion Model Sampling Diffusion Models
School of Mathematical Sciences, Tel Aviv University, Israel.
Diffusion Score Estimation with Shallow Neural Networks: Regularity, Approximation, and Finite-Sample Rates
Oct 19, 2026Fan Liu, Yahong Yang, Wei ZhuScore-Based Generative Modeling Diffusion Models
School of Mathematics, Georgia Institute of Technology, USA · Department of Mathematics and Statistics, Binghamton University, USA
LEAP: Accelerating ODE-based Diffusion Sampling with Optimal Linear Leaps
Oct 19, 2026Haowei Zheng, Zhenyu Zhou, Jiawei Chen +2Diffusion Model Sampling Diffusion Model Acceleration
State Key Laboratory of Blockchain and Data Security, Zhejiang University. · Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security. · University of California, Berkeley, California, United States
Data Free Training of Diffusion Models for Lattice Field Theories
Oct 13, 2026Dennis Grinwald, Ankur Singha, Khaled Kahouli +2Lattice Field Theory Diffusion Model Sampling
Berlin Institute for the Foundations of Learning and Data (BIFOLD), Germany · Technische Universität Berlin, Germany · Deutsches Elektronen-Synchrotron (DESY), Platanenallee 6, 15738 Zeuthen, Germany +2
Uncovering the Generative Landscape of Diffusion Models: A Spectral-Guided Quality-Diversity Diffusion Framework
Oct 11, 2026Hannah Janmohamed, Joao Correia, Penousal Machado +1Diffusion Model Sampling Quality-Diversity Optimization
University of Coimbra
Controllable Diverse Sampling through Pullback Directions
Oct 9, 2026Sylvain Dehayem Kenfouo, Aaron Zweig, Mingxuan Zhang +1Image Generation Diffusion Model Sampling
École Polytechnique, Institut Polytechnique de Paris · New York Genome Center · Irving Institute for Cancer Dynamics, Columbia University +4
Correction Training for Diffusion Models
Oct 9, 2026Donghoon Ahn, Runqian Wang, Alexei A. Efros +2Diffusion-Based Image Generation Diffusion Models
University of California, Berkeley · Reve
MAST: Motif-Augmented Diffusion with Search Tree for Spectroscopic Molecular Structure Elucidation
Oct 8, 2026Chenghao Jia, Mengdi Liu, Hong Chang +2Molecular Generation Diffusion Sampling
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, China · University of Chinese Academy of Sciences, China
Equal Path Cost, Unequal Output Effects: Understanding Perturbation Propagation in Diffusion Models
Oct 8, 2026Wei Guo, Yaowen Zhang, Xingtong Ge +1Diffusion Models Diffusion Model Sampling
iComAI Lab, The Hong Kong University of Science and Technology · Department of Physics, The Hong Kong University of Science and Technology
Steering Diffusion Models to Rare Events with Sequential Monte Carlo
Oct 6, 2026Aavash Subedi, Tim Reichelt, Christopher Williams +3Diffusion Model Sampling Importance Sampling
Department of Statistics, University of Oxford · Department of Physics, University of Oxford · Department of Statistics, University of British Columbia
When Does a Diffusion Model Decide What to Draw ?
Oct 5, 2026Snigdha Chandan KhilarDiffusion Model Sampling Diffusion Models
Independent Researcher
LatticeSMC: Where to Spend Inference-Time Compute in Chunked Sequence Generators
Oct 2, 2026Xuanchen Wang, Heng Wang, Weidong CaiInference-Time Guidance Diffusion Model Sampling
School of Computer Science The University of Sydney Sydney, NSW, Australia
Error-Corrected Inference-Time Scaling for Imperfect Diffusion Models
Oct 1, 2026Zuokai Wen, Louis Grenioux, Weinan E +1Markov Chain Monte Carlo Diffusion Model Sampling
School of Artificial Intelligence, Shanghai Jiao Tong University · Center for Computational Mathematics, Flatiron Institute · School of Mathematical Sciences, Peking University
PhysDEM: Physics-Defined Energy-Matching Diffusion for Spatiotemporal Field Generation under Scarce Measurements
Oct 1, 2026Zhenyu Liang, Yining Huang, Yubo Zhao +1Physics-Informed Diffusion Models Physics-Informed Generative Modeling
HKUST · UT Austin
Sharp Convergence and Sampling Trade-offs for Riemannian Diffusion under Nonnegative Ricci Curvature
Sep 29, 2026Yuhao Liu, Longbo HuangDiffusion Model Sampling Diffusion Models
Institute for Interdisciplinary Information Sciences, Tsinghua University
Atlases Are Already Inside: Recovering Population Templates from Pretrained Diffusion Models
Sep 24, 2026Jian Shi, John Femiani, Peter WonkaDiffusion Models Diffusion Model Sampling
KAUST · Miami University
Accurate Sampling from Diffusion Models
Sep 24, 2026Dénes SextyLattice Field Theory Diffusion Model Sampling
Institute of Physics, NAWI Graz, University of Graz, Universitätsplatz 5, 8010 Graz, Austria
Mean Velocity Matching: Rethinking Generative Dynamics in Diffusion Models
Sep 21, 2026Yunhong Zhang, Changjie Cao, Zhihua Zhang +4Diffusion Model Sampling Diffusion Models
Chengdu University of Technology, Chengdu, China · Peking University, Beijing, China · University of Electronic Science and Technology of China, Chengdu, China
Efficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion Models
Sep 15, 2026Kuluhan Binici, Cihan Acar, Shivam Aggarwal +2Diffusion Model Sampling Diffusion Timestep Scheduling
1SAP · 2National University of Singapore · Institute for Infocomm Research (I2R), A*STAR, Singapore
A Splitting Method for SDE Terminal-Law Estimation
Sep 11, 2026Rushil Gupta, Sandeep JunejaStochastic Differential Equations Diffusion Model Sampling
Safexpress Centre for Data, Learning and Decision Sciences Ashoka University
Provably adaptive sampling with uniform and remasking discrete diffusion models
Aug 24, 2026Daniil Dmitriev, Zhihan Huang, Yuting WeiDiffusion Model Sampling Diffusion Models
Department of Statistics and Data Science, the Wharton School, University of Pennsylvania
Improved denoising diffusion probabilistic models with efficient non-diagonal covariance modeling
Aug 22, 2026Rui Xia, Ayan Das, Artem Artemev +3Diffusion Models Diffusion Model Sampling
University of Cambridge, UK · King’s College London, UK · MediaTek Research, UK +1
A Plug-in Interpretation of Conditioning in Score-Based Diffusion Models
Aug 19, 2026Libo Chen, Souvik Ghosh, Teo Deveney +2Conditional Diffusion Models Diffusion Model Sampling
University of Bath, Bath, UK · International Institute of Information Technology Hyderabad, India
A Frozen Pixel-Space Diffusion Model Can Guide Itself with Its Own Samples
Jul 31, 2026Zixuan Fu, Chong Wang, Lanqing Guo +3Diffusion Model Guidance Diffusion Model Sampling
Nanyang Technological University
Rethinking the Generation Order of Block Diffusion Language Models
Jul 27, 2026Kai Syun Hou, James KwokDiffusion Model Sampling Blockwise Diffusion Language Models
Department of Computer Science and Engineering The Hong Kong University of Science and Technology
Manifold-Constrained Noise Optimization for Diverse Diffusion Sampling
Jul 27, 2026Qitan Shi, Cheng Jin, Ziyuan Liu +1Diffusion Model Sampling Image Generation
Tsinghua University
Learning Sampling Parameters for Diffusion Models
Jul 26, 2026Arisrei Lim, Yossi GandelsmanDiffusion Model Guidance Diffusion Model Sampling
Reve
From Score Learning to Discretized Sampling: An End-to-End Generalization Analysis of Diffusion Models
Jul 25, 2026Jinshu Huang, Yiming Jiang, Chunlin WuDiffusion Model Sampling Score-Based Generative Modeling
School of Mathematical Sciences, Nankai University, Tianjin, China
Inference-Time Scaling of Diffusion Models via Progressive Seed Pruning
Jul 23, 2026Rogerio Guimaraes, Pietro PeronaDiffusion Model Sampling Diffusion Sampling
California Institute of Technology, Pasadena CA 91125, USA

Oct 29, 2026J/K move · Enter open · S save

An ODE-based Sampler for Discrete Diffusion Models

Samson Gourevitch, Yazid Janati, Eric Moulines, Eric P. Xing+2

CMAP, Ecole polytechnique · Institute of Foundation Models · MBZUAI+2

Diffusion Model Sampling Diffusion Models Diffusion Sampling

Open paper AskPDF arXiv

The marginals of a continuous diffusion model can be reproduced by a deterministic ordinary differential equation (ODE), known as the probability flow ODE, which provides a foundation for accelerated sampling and consistency distillation. In this paper we address the question whether an analogous formulation exists for discrete diffusion models and answer it affirmatively by introducing exponential residual flows (ERFs). Our framework augments the discrete state with a continuous residual variable for each token and position. These residuals evolve deterministically according to piecewise-defined ODEs whose vector fields depend on the current discrete state and the forward and backward rate matrices of the prescribed diffusion model. The discrete state changes whenever a residual reaches zero. We prove that this construction preserves the marginals of the original diffusion. We derive a practical discretization of our sampler and specialize it to masked and uniform diffusion. The deterministic trajectories of ERFs support consistency distillation and yield empirical improvements over previous approaches across a variety of benchmarks including code and text generation tasks.