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.

Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing
Apr 20, 2026Kijung Jeon, Michael Muehlebach, Molei TaoConstrained Generative Modeling Langevin Dynamics
Georgia Institute of Technology · Max Planck Institute for Int. Sys.
Interpolating Discrete Diffusion Models with Controllable Resampling
Apr 19, 2026Marcel Kollovieh, Sirine Ayadi, Stephan GünnemannDiffusion Model Sampling Molecular Graph Generation
School of Computation, Information and Technology, Technical University of Munich
Elucidating the SNR-t Bias of Diffusion Probabilistic Models
Apr 17, 2026Meng Yu, Lei Sun, Jianhao Zeng +2Diffusion Model Sampling Diffusion Sampling
Lanzhou University · AMAP Alibaba Group
SCoRe: Clean Image Generation from Diffusion Models Trained on Noisy Images
Apr 10, 2026Yuta Matsuzaki, Seiichi Uchida, Shumpei TakezakiDiffusion-Based Image Generation Diffusion Models
Kyushu University, Fukuoka, Japan
VASR: Variance-Aware Systematic Resampling for Reward-Guided Diffusion
Apr 8, 2026Shivanshu Shekhar, Sagnik Mukherjee, Jia Yi Zhang +1Diffusion Model Sampling Diffusion Sampling
Siebel School of Computing and Data Science University of Illinois Urbana-Champaign · Department of Statistics University of Illinois Urbana-Champaign
Bias mitigation in graph diffusion models
Apr 2, 2026Meng Yu, Kun ZhanDiffusion Models Graph Diffusion
School of Information Science & Engineering, Lanzhou University
DRiffusion: Draft-and-Refine Process Parallelizes Diffusion Models with Ease
Mar 26, 2026Runsheng Bai, Chengyu Zhang, Yangdong DengDiffusion Model Sampling Diffusion Model Inference Acceleration
CSAIL, MIT · IST, Nanjing University · School of Software, Tsinghua University; FuturististAI Lab, Shanghai Tsinghua International Innovation Center
Efficient Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution
Mar 22, 2026Yu-Shan Tai, An-Yeu, WuDiffusion Model Sampling Diffusion Sampling
Andy · Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan
Q-Drift: Quantization-Aware Drift Correction for Diffusion Model Sampling
Mar 18, 2026Sooyoung Ryu, Mathieu Salzmann, Saqib JavedDiffusion Model Quantization Diffusion Model Sampling
Department of Computer Science and Engineering, Seoul National University, Seoul, South Korea · School of Computer and Communication Sciences, EPFL, Lausanne, Switzerland · Meta Reality Labs, Redmond, USA
Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models
Mar 15, 2026Niklas Schweiger, Daniel Cremers, Karnik RamDiffusion Model Alignment Black-Box Optimization
Technical University of Munich, Germany · Munich Center for Machine Learning, Germany
Draft-and-Target Sampling for Video Generation Policy
Mar 13, 2026Qikang Zhang, Yingjie Lei, Wei Liu +1Diffusion Model Inference Acceleration Diffusion Model Sampling
South China Normal University · University of Western Australia
Synergizing Transport-Based Generative Models and Latent Geometry for Stochastic Closure Modeling
Feb 19, 2026Xinghao Dong, Huchen Yang, Jin-long WuDiffusion Model Sampling Flow Matching
Department of Mechanical Engineering, University of Wisconsin–Madison, Madison, WI 53706
Efficient Generative Modeling beyond Memoryless Diffusion via Adjoint Schrödinger Bridge Matching
Feb 17, 2026Jeongwoo Shin, Jinhwan Sul, Joonseok Lee +2Diffusion Model Sampling Schrödinger Bridges
Seoul National University, Seoul, Korea · Georgia Institute of Technology, Atlanta, GA, USA · Sungkyunkwan University, Seoul, Korea
Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees
Feb 16, 2026Daniil Dmitriev, Zhihan Huang, Yuting WeiSample Complexity Diffusion Model Sampling
Department of Statistics and Data Science, the Wharton School, University of Pennsylvania
Formalizing the Sampling Design Space of Diffusion-Based Generative Models via Adaptive Solvers and Wasserstein-Bounded Timesteps
Feb 13, 2026Sangwoo Jo, Sungjoon ChoiDiffusion Model Sampling Diffusion Sampling
Department of Artificial Intelligence, Korea University, Seoul, South Korea.
Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models
Feb 8, 2026Lior Cohen, Ofir Nabati, Kaixin Wang +2Reinforcement Learning World Model Learning
Technion · Microsoft Research
A Random Matrix Theory Perspective on the Consistency of Diffusion Models
Feb 2, 2026Binxu Wang, Jacob Zavatone-Veth, Cengiz PehlevanDiffusion Model Sampling ML Reproducibility
Kempner Institute, Harvard University, Boston, MA, USA · Center for Brain Science, Harvard University, Cambridge, MA, USA · Society of Fellows, Harvard University, Cambridge, MA, USA +1
Control Variate Score Matching for Diffusion Models
Dec 23, 2025Khaled Kahouli, Romuald Elie, Klaus-Robert Müller +3Score Matching Sampling from Unnormalized Distributions
1Google DeepMind · 2BIFOLD – Berlin Institute for the Foundations of Learning and Data · 3Machine Learning Group, Technische Universität Berlin +2
Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion
Oct 6, 2025Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi +2Diffusion Model Sampling Diffusion Sampling
Sony Group Corporation · Sony AI · The University of Tokyo
MACS: Measurement-Aware Consistency Sampling for Inverse Problems
Oct 2, 2025Amirreza Tanevardi, Pooria Abbas Rad Moghadam, Seyed Mohammad Eshtehardian +2Diffusion Model Sampling Inverse Problems
Department of Electrical Engineering Sharif University of Technology Tehran, Iran · Electronics Research Institute Sharif University of Technology Tehran, Iran
Fast Convergence for High-Order ODE Solvers in Diffusion Probabilistic Models
Jun 16, 2025Daniel Zhengyu Huang, Jiaoyang Huang, Zhengjiang LinDiffusion Model Sampling Diffusion Sampling
Beijing International Center for Mathematical Research, Center for Machine Learning Research, Peking University, Beijing, China · Department of Statistics and Data Science, University of Pennsylvania, Philadelphia, PA, USA · Department of Mathematics, Massachusetts Institute of Technology, 77 Massachusetts Ave, 02139 Cambridge MA, USA
Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models
Feb 12, 2025Khaled Kahouli, Winfried Ripken, Stefan Gugler +3Diffusion Model Sampling Diffusion Timestep Scheduling
BIFOLD – Berlin Institute for the Foundations of Learning and Data · Machine Learning Group, Technische Universität Berlin · Google DeepMind +3

Apr 20, 2026J/K move · Enter open · S save

Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing

Kijung Jeon, Michael Muehlebach, Molei Tao

Georgia Institute of Technology · Max Planck Institute for Int. Sys.

Constrained Generative Modeling Langevin Dynamics Diffusion Model Sampling Diffusion Model Inference Acceleration Diffusion Models Constrained Sampling

Open paper AskPDF arXiv

Generative modeling within constrained sets is essential for scientific and engineering applications involving physical, geometric, or safety requirements (e.g., molecular generation, robotics). We present a unified framework for constrained diffusion models on generic nonconvex feasible sets

Σ

that simultaneously enforces equality and inequality constraints throughout the diffusion process. Our framework incorporates both overdamped and underdamped dynamics for forward and backward sampling. A key algorithmic innovation is a computationally efficient landing mechanism that replaces costly and often ill-defined projections onto

Σ

, ensuring feasibility without iterative Newton solves or projection failures. By leveraging underdamped dynamics, we accelerate mixing toward the prior distribution, effectively alleviating the high simulation costs typically associated with constrained diffusion. Empirically, this approach reduces function evaluations and memory usage during both training and inference while preserving sample quality. On benchmarks featuring equality and mixed constraints, our method achieves comparable sample quality to state-of-the-art baselines while significantly reducing computational cost, providing a practical and scalable solution for diffusion on nonconvex feasible sets.