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

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

Why DDIM Hallucinates More Than DDPM: A Theoretical Analysis of Reverse Dynamics
May 7, 2026Muhammad H. Ashiq, Samanyu Arora, Abhinav N. Harish +3Diffusion Sampling Diffusion Models
University of Wisconsin-Madison, Madison, WI, USA.
Diverse Sampling in Diffusion Models with Divergence-Free Particle Guidance
May 7, 2026Gal Vinograd, Idan Achituve, Ethan FetayaDiffusion Model Guidance Diffusion Sampling
Faculty of Engineering Bar-Ilan University Ramat Gan, Israel · Independent Researcher
Diffusion-Based Posterior Sampling: A Feynman-Kac Analysis of Bias and Stability
May 7, 2026William Porteous, Advait Parulekar, Sebastien Motsch +2Stochastic Differential Equations Bayesian Inverse Problems
Department of Mathematics, UT Austin. · Department of Electrical and Computer Engineering, UT Austin. · School of Mathematical and Statistical Sciences, Arizona State University.
Diffusion model for SU(N) gauge theories
May 7, 2026Javad Komijani, Marina K. Marinkovic, Lara TurgutScore Matching Diffusion Sampling
Institute for Theoretical Physics, ETH Zurich, 8093 Zurich, Switzerland
DBMSolver: A Training-free Diffusion Bridge Sampler for High-Quality Image-to-Image Translation
May 7, 2026Sankarshana Venugopal, Mohammad Mostafavi, Jonghyun ChoiImage-to-Image Translation Diffusion Sampling
Seoul National University · ECE, IPAI, ASRI in SNU
Conditional Diffusion Sampling
May 5, 2026Francisco M. Castro-Macías, Pablo Morales-Álvarez, Saifuddin Syed +3Markov Chain Monte Carlo Sampling from Unnormalized Distributions
University of Granada · Work done while visiting the University of Cambridge. · University of British Columbia +2
Flow Sampling: Learning to Sample from Unnormalized Densities via Denoising Conditional Processes
May 5, 2026Aaron Havens, Brian Karrer, Neta ShaulSampling from Unnormalized Distributions Diffusion Sampling
FAIR at Meta · Weizmann Institute of Science
SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking
May 4, 2026Zhengan Yan, Shikang Zheng, Haoran Qin +9Diffusion Sampling Diffusion-Based Image Editing
EPIC Lab , Shanghai Jiao Tong University · Shandong University · Alibaba Group +2
IdentiFace: Multi-Modal Iterative Diffusion Framework for Identifiable Suspect Face Generation in Crime Investigations
May 1, 2026Weichen Liu, Yixin Yang, Changsheng Chen +1Diffusion Sampling Image Generation
Southeast University · Nanjing, China · Shenzhen MSU-BIT University +1
Information-geometric adaptive sampling for graph diffusion
Apr 30, 2026Yuhui Lu, Wenjing Liu, Kun ZhanInformation Geometry Graph Generation
School of Information Science and Engineering, Lanzhou University, Gansu, China.
A unified perspective on fine-tuning and sampling with diffusion and flow models
Apr 30, 2026Carles Domingo-Enrich, Yuanqi Du, Michael S. AlbergoStochastic Optimal Control Diffusion Sampling
Microsoft Research New England · Harvard University, Kempner Institute
BiMol-Diff: A Unified Diffusion Framework for Molecular Generation and Captioning
Apr 27, 2026Aditya Hemant Shahane, Anuj Kumar Sirohi, Devansh Arora +3Diffusion Sampling Molecular Generation
Indian Institute of Technology Delhi · Indian Institute of Technology Ropar · Indian Institute of Science Bengaluru
$Z^2$ -Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models
Apr 26, 2026Haosen Li, Wenshuo Chen, Shaofeng Liang +3Diffusion Model Alignment Diffusion Sampling
1The Hong Kong University of Science and Technology (Guangzhou) · 2Griffith University & Data61/CSIRO
FASTER: Value-Guided Sampling for Fast RL
Apr 21, 2026Perry Dong, Alexander Swerdlow, Dorsa Sadigh +1Diffusion Sampling Diffusion Policy
Stanford University
Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation
Apr 21, 2026Johannes Schusterbauer, Ming Gui, Yusong Li +3Diffusion Model Sampling Diffusion Sampling
Noise-Adaptive Diffusion Sampling for Inverse Problems Without Task-Specific Tuning
Apr 18, 2026Yingzhi Xia, Setthakorn Tanomkiattikun, Liangli Zhen +1Markov Chain Monte Carlo Bayesian Inverse Problems
Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore · Agency for Science, Technology and Research, Singapore · Johns Hopkins University +1
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
Query Lower Bounds for Diffusion Sampling
Apr 12, 2026Zhiyang Xun, Eric PriceQuery Complexity Diffusion Sampling
UT Austin
From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic Horizons
Apr 11, 2026Xiangyu Ma, Teng Xiao, Zuchao Li +1Diffusion Language Models Diffusion Language Model Inference
School of Artificial Intelligence, Wuhan University, Wuhan, China · School of Computer Science, Wuhan University, Wuhan, China
EGLOCE: Training-Free Energy-Guided Latent Optimization for Concept Erasure
Apr 10, 2026Junyeong Ahn, Seojin Yoon, Sungyong BaikDiffusion Model Unlearning Safe T2I Generation
KAIST AI · Hanyang University
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
1.x-Distill: Breaking the Diversity, Quality, and Efficiency Barrier in Distribution Matching Distillation
Apr 5, 2026Haoyu Li, Tingyan Wen, Lin Qi +6Diffusion Model Distillation Diffusion Sampling
Tsinghua University · Central Media Technology Institute, Huawei
Generating DDPM-based Samples from Tilted Distributions
Apr 3, 2026Himadri Mandal, Dhruman Gupta, Rushil Gupta +5Diffusion Sampling Constrained Generative Modeling
Indian Statistical Institute, Kolkata. · Ashoka University. · Tata Institute of Fundamental Research +2
Why Gaussian Diffusion Models Fail on Discrete Data and How to Prevent It?
Apr 2, 2026Alexander Shabalin, Simon Elistratov, Viacheslav Meshchaninov +2Diffusion Models Diffusion Sampling
Constructor University, Bremen, Germany · Lomonosov Moscow State University, Moscow, Russia
Locally Confident, Globally Stuck: The Quality-Exploration Dilemma in Diffusion Language Models
Apr 1, 2026Liancheng Fang, Aiwei Liu, Henry Peng Zou +7Diffusion Language Model Decoding Diffusion Sampling
University of Illinois Chicago · Tsinghua University · MBZUAI +1
Total Variation Guarantees for Sampling with Stochastic Localization
Mar 31, 2026Jakob KellermannSampling from Unnormalized Distributions Diffusion Sampling
Weierstrass Institute Berlin
Stepwise Credit Assignment for GRPO on Flow-Matching Models
Mar 30, 2026Yash Savani, Branislav Kveton, Yuchen Liu +5RL for Diffusion Models Step-Level Credit Assignment in RL
Carnegie Mellon University · Adobe Research
A Priori Sampling of Transition States with Guided Diffusion
Mar 26, 2026Hyukjun Lim, Soojung Yang, Lucas Pinède +3Diffusion Model Guidance Diffusion Sampling
Department of Materials Science and Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, 08826, Republic of Korea. · Computational and Systems Biology, MIT, 77 Massachusetts Avenue, Cambridge, 02139, Massachusetts, USA. · Chimie ParisTech, PSL University, 11 rue Pierre et Marie Curie, Paris, 75005, France. +2
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
Polynomial Speedup in Diffusion Models with the Multilevel Euler-Maruyama Method
Mar 25, 2026Arthur JacotDiffusion Model Inference Acceleration Diffusion Sampling

May 7, 2026J/K move · Enter open · S save

Why DDIM Hallucinates More Than DDPM: A Theoretical Analysis of Reverse Dynamics

Muhammad H. Ashiq, Samanyu Arora, Abhinav N. Harish, Ishaan Kharbanda+2

University of Wisconsin-Madison, Madison, WI, USA.

Diffusion Sampling Diffusion Models

Open paper AskPDF arXiv

We theoretically study the hallucination phenomena in two canonical diffusion samplers: the stochastic Denoising Diffusion Probabilistic Model (DDPM) and the deterministic Denoising Diffusion Implicit Model (DDIM). We analyze the reverse ODE (DDIM) and SDE (DDPM) for a Gaussian mixture target, proving that after a critical time

τ

, (a) DDIM can become stuck on the segment connecting the two nearest modes and (b) DDPM stochasticity helps it become unstuck from this region, thus avoiding hallucination. Our empirical validation verifies that DDPM has a significantly lower hallucination rate than DDIM when this region is entered. Building on our observations, we exhibit how using additional stochastic steps can help DDIM avoid hallucinations and offer new insights on how to design improved samplers.