Diffusion Models

Follow this topic Ask about this topic

Diffusion models learn a data distribution by gradually corrupting examples with noise and training a denoiser to reverse that process. Major approaches include DDPMs and score-based SDEs, latent diffusion and diffusion Transformers, flow and consistency methods, and discrete masked or continuous-time Markov diffusion; conditioning and guidance adapt them to specific tasks. They are used for images, video, audio, language, molecules, and scientific forecasting, with evaluations ranging from ImageNet FID to language perplexity and domain-specific measures of accuracy and uncertainty. A central tension is how to make sampling faster and generation more controllable without sacrificing quality, calibration, or diversity, while theory and ongoing audits address generalization, memorization, and privacy.

Latest papers

1,192 papers152 papers in the last four weeks, up 77% on the four weeks before. 0.9% 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
Difficulty Calibration Across Time for Membership Inference in Diffusion Models
Oct 29, 2026Michael Joseph, Yedid HoshenMembership Inference Attacks Diffusion Models
The Hebrew University of Jerusalem
HairDeck: Animation-Ready Stylized Hair Cards from a Single Image
Oct 29, 2026Yuze He, Yixiang Wei, Wang Zhao +33D Asset Generation Articulated 3D Asset Generation
Tsinghua University · Carnegie Mellon University · The Chinese University of Hong Kong
Numerical Integration on Bounded Domains via Learned Reflected Diffusions
Oct 29, 2026Kirill Korolev, Artur Goldman, Timofei Gritsaev +2Numerical Integration Importance Sampling
HSE University · ETH Zürich, ETH AI Center · Constructor University
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.
UniRA: Unified Representation Alignment and Auto-Encoding for Efficient Diffusion Generation
Oct 29, 2026An Lanji, Dawei Liu, Jin Li +3Diffusion-Based Image Generation Diffusion Models
University of Electronic Science and Technology of China, Chengdu, China.
Diffusion models for the $O(3)$ nonlinear sigma model
Oct 29, 2026Daniel SchubringDiffusion Models
Department of Physics, City College of New York, CUNY New York, NY 10031, USA
Skillful and realistic precipitation forecasting with reinforced diffusion
Oct 28, 2026Ozan Sener, Anand Avati, David Hafner +7Precipitation Forecasting Diffusion Models
Apple · ETH Zurich · Colorado State University
Hierarchical Diffusion for Camera-controlled Autoregressive Video Generation
Oct 27, 2026Kaihua Chen, Yiming Gong, Deva Ramanan +1Camera-Controlled Video Generation Long-Horizon Video Generation
Carnegie Mellon University, Pittsburgh, PA, USA · University of Oxford, Oxford, UK
Taming Noise Initialization for Zero-shot Video Restoration with Image Diffusion Priors
Oct 27, 2026Chong Wang, Zixuan Fu, Hao Cheng +3Video Restoration Diffusion Models
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore · School of Artificial Intelligence, Hebei University of Technology, Tianjin, China · Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Stockholm, Sweden +1
A First-Step Bias Restores Lost Diversity in Diffusion Model Distillation
Oct 27, 2026Wenwu Tang, Dong Wang, Yun Cheng +1Diffusion Model Distillation Diffusion Models
Graz University of Technology · Swiss Data Science Center, Switzerland · Complexity Science Hub, Austria
Provenance Signatures for Low Rank Adaptations of Image Diffusion Models
Oct 27, 2026Tobias Cheung, Mohan Dantam, Marc Juarez +1Diffusion Models
University of Edinburgh · University of Oxford
Generative Refinement Learning for Temporal Interpolation in Scientific Machine Learning
Oct 27, 2026Pu Ren, Michael W. Mahoney, N. Benjamin ErichsonScientific ML Residual Learning
Lawrence Berkeley National Lab · International Computer Science Institute · University of California, Berkeley
Quantifying the failure of symmetry learning in linear diffusion models due to initialization and finite-sample effects
Oct 26, 2026John J. Vastola, Kanaka RajanSymmetry Breaking Diffusion Models
Department of Neurobiology, Harvard Medical School · Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University
NOMAD-EEG: Native Omni-Montage Adaptive Diffusion
Oct 26, 2026Abdulkader Helwan, Khadidja Henni, Lina Abou-AbbasElectroencephalography EEG Foundation Models
Department of Electrical and Computer Engineering, Lebanese American University, Byblos, Lebanon · Institute of Applied Artificial Intelligence, TÉLUQ University, Montreal, Canada
Generative AI in Turbulence: Foundations, Applications, Validations and Benchmarks
Oct 26, 2026Luca Biferale, Michele BuzzicottiGenerative Modeling Generative AI Evaluation
Department of Physics and INFN, University of Rome Tor Vergata, Rome, Italy
The Noise-Transmission Burden of Diffusion Network: Why Image Prediction Can Outperform Noise Prediction
Oct 26, 2026Gyeonghun Kang, Pengxi Liu, Bingshuo Qian +1Diffusion-Based Denoising Diffusion Models
Duke University, Durham, NC, USA
Cumulative Marginal Matching for One-Step Diffusion
Oct 25, 2026Paribesh Regmi, Rui LiOne-Step Generative Modeling Few-Step Diffusion Sampling
Rochester Institute of Technology, Rochester, NY, US
Conditional Diffusion Generation of DVL and Inertial Signals for Underwater Navigation
Oct 25, 2026Michal Levin, Itzik KleinSynthetic Data Generation Autonomous Underwater Navigation
University of Haifa, Abba Khoushy Ave 199, Haifa, 3498838, Israel
Freeze What Is Settled, Cache What Is Smooth: Spatial Freezing Keeps Step Caching in Its Low-Error Regime
Oct 25, 2026Baiyan Li, Ganxuan YangDiffusion Model Inference Acceleration Diffusion-Based Image Editing
Lancaster University · Beijing Jiaotong University
Information-Theoretic Scaling Laws for Generative Diffusion Training
Oct 23, 2026Druv Pai, Dejan Stancevic, Yi Ma +1Diffusion Models Memorization in Generative Models
UC Berkeley · Radboud University · HKU, UC Berkeley
Support-guided OOD Removal with Diffusion
Oct 23, 2026Alireza Kheirandish, Sara Fridovich-KeilDiffusion Models for Image Restoration Diffusion Models
Georgia Institute of Technology, Atlanta, GA, USA
LLaCO: Continuous Diffusion for Large Language Models with Competition-Aware Semantic Scheduling
Oct 23, 2026Zijian Jia, Peixuan Zhang, Genying Li +5Diffusion Language Models Continuous Diffusion Language Models
School of Artificial Intelligence, Beijing University of Posts and Telecommunications · Yuanpei College, Peking University · Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance +3
ParaLin++: Accelerating Parallel Diffusion Integrator via Intrinsic Partially Linear Structure
Oct 22, 2026Jianrong Lu, Zhiyu Zhu, Hui Liu +1Diffusion Sampling Diffusion Model Inference Acceleration
the Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China · City University of Hong Kong (Dongguan), Dongguan, China · the School of Computing and Information Sciences, Saint Francis University, Hong Kong SAR, China
DiffLTM: Continuous Diffusions Large Tabular Models for Conditional Generation
Oct 21, 2026Alankrita Bhatt, Mukur Gupta, Andrea Montanari +1Tabular Diffusion Models Synthetic Tabular Data Generation
Granica Computing Inc. · Stanford University
Seeing through Denoising: Frequency-guided One-step Denoising for Infrared Small Target Detection
Oct 21, 2026Xuelin Qian, Zixuan Wang, Chang Xu +2Infrared Small Target Detection Diffusion Models
Internal Guidance as a Sampling Method for Tilted Diffusion Models
Oct 21, 2026Curtis McDonald, Peter BartlettDiffusion Model Guidance Diffusion Sampling
Simons Institute, University of California Berkeley · Google DeepMind
Policy-Mask: Budget-Aware Adaptation of Diffusion Features to Discriminative Tasks
Oct 20, 2026Ivan Listopadov, Maksim Nakhodnov, Aibek AlanovDiffusion Model Adaptation Feature Selection
HSE University · MSU · Constructor University +1
Continual Concept Personalization in Diffusion Models via Residual-Space Adaptation
Oct 20, 2026Yuzhi Liu, Enis Simsar, Giulia Lanzillotta +1Diffusion Model Adaptation T2I Diffusion Models
ETH Zürich
Binary Discrete Diffusion: Candidate-Set Diffusion for Logic and Planning Tasks
Oct 20, 2026Rodrigo Casado Noguerales, Dimitri von Rütte, Bernhard Schölkopf +2Diffusion Models Diffusion-Based Planning
ETH Zurich · Max Planck Institute for Intelligent Systems · ELLIS Institute Tübingen

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.