Diffusion Models

Ask about this topic

Overview

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

CardsList

1,192 papers152 papers in the last four weeks, up 77% on the four weeks before. 0.9% of all new papers.

  1. Generative models on phase space

    Apr 2, 2026Zachary Bogorad, Ibrahim Elsharkawy, Yonatan Kahn +2Generative ModelingConstrained Generative Modeling

    Theory Division, Fermi National Accelerator Laboratory, Batavia, IL, USA · Department of Physics, University of Toronto and Vector Institute, Toronto, ON, Canada and NERSC, Lawrence Berkeley National Laboratory, Berkeley, California, USA · Department of Physics, University of Toronto and Vector Institute, Toronto, ON, Canada +2

  2. Why Gaussian Diffusion Models Fail on Discrete Data and How to Prevent It?

    Apr 2, 2026Alexander Shabalin, Simon Elistratov, Viacheslav Meshchaninov +2Diffusion ModelsDiffusion Sampling

    Constructor University, Bremen, Germany · Lomonosov Moscow State University, Moscow, Russia

  3. Bias mitigation in graph diffusion models

    Apr 2, 2026Meng Yu, Kun ZhanDiffusion ModelsGraph Diffusion

    School of Information Science & Engineering, Lanzhou University

  4. Why Instruction-Based Unlearning Fails in Diffusion Models?

    Apr 2, 2026Zeliang Zhang, Rui Sun, Jiani Liu +2Diffusion Model UnlearningMachine Unlearning

    University of Rochester · UCLA · UCSB

  5. Data-Driven Reachability Analysis via Diffusion Models with PAC Guarantees

    Mar 31, 2026Yanliang Huang, Peng Xie, Wenyuan Wu +2Reachability AnalysisDiffusion Models

    School of Computation, Information and Technology, Technical University of Munich, Munich, Germany. · School of Engineering, Hainan Bielefeld University of Applied Sciences, Hainan, China.

  6. Video Models Reason Early: Exploiting Plan Commitment for Maze Solving

    Mar 31, 2026Kaleb Newman, Tyler Zhu, Olga RussakovskyVideo Diffusion ModelsVideo Reasoning

    Princeton University

  7. Diffusion-Based Feature Denoising with NNMF for Robust handwritten digit multi-class classification

    Mar 31, 2026Hiba Adil Al-kharsan, Róbert RajkóDiffusion-Based DenoisingHandwritten Digit Recognition

    Doctoral School of Computer Science, University of Szeged, Árpád tér 2, H-6720 Szeged, Hungary · University Research and Innovation Center (EKIK), Óbuda University, Bécsi út 96/b, H-1034 Budapest, Hungary

  8. SHIFT: Stochastic Hidden-Trajectory Deflection for Removing Diffusion-based Watermark

    Mar 31, 2026Rui Bao, Zheng Gao, Xiaoyu Li +3Watermark RemovalDiffusion Model Watermarking

    University of New South Wales · Griffith University

  9. Emotion Diffusion Classifier with Adaptive Margin Discrepancy Training for Facial Expression Recognition

    Mar 31, 2026Rongkang Dong, Cuixin Yang, Cong Zhang +2Adversarial RobustnessFacial Expression Recognition

    Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong · School of Control Science and Engineering, Shandong University

  10. iPoster: Content-Aware Layout Generation for Interactive Poster Design via Graph-Enhanced Diffusion Models

    Mar 31, 2026Xudong Zhou, Jinyuan Liang, Qiuyi Guo +1Constrained Generative ModelingDiffusion Models

    Beijing Institute of Technology, Beijing, China

  11. Diffusion Mental Averages

    Mar 31, 2026Phonphrm Thawatdamrongkit, Sukit Seripanitkarn, Supasorn SuwajanakornDiffusion ModelsT2I Diffusion Models

    VISTEC, Thailand

  12. Unrestrained Simplex Denoising for Discrete Data. A Non-Markovian Approach Applied to Graph Generation

    Mar 30, 2026Yoann Boget, Alexandros KalousisGenerative ModelingDiffusion Models

    Department of Computer Science, University of Geneva, Switzerland · DMML Group, Geneva School for Business administration HES-SO, Switzerland

  13. Downscaling weather forecasts from Low- to High-Resolution with Diffusion Models

    Mar 30, 2026Joffrey Dumont Le Brazidec, Simon Lang, Martin Leutbecher +9Weather ForecastingProbabilistic Forecasting

    European Centre for Medium-Range Weather Forecasts (ECMWF)

  14. ColorFLUX: A Structure-Color Decoupling Framework for Old Photo Colorization

    Mar 30, 2026Bingchen Li, Zhixin Wang, Fan Li +5Image RestorationImage-to-Image Translation

    University of Science and Technology of China · Huawei Noah’s Ark Lab

  15. From Independent to Correlated Diffusion: Generalized Generative Modeling with Probabilistic Computers

    Mar 30, 2026Nihal Sanjay Singh, Mazdak Mohseni-Rajaee, Shaila Niazi +1Diffusion ModelsPhysics-Informed Generative Modeling

    Department of Electrical and Computer Engineering, University of California, Santa Barbara, Santa Barbara, CA, 93106, USA

  16. Beyond Dataset Distillation: Lossless Dataset Concentration via Diffusion-Assisted Distribution Alignment

    Mar 30, 2026Tongfei Liu, Yufan Liu, Bing Li +1Dataset DistillationDataset Condensation

    State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chines Academy of Sciences, 95 Zhongguancun East Road, Beijing, 100190, Beijing, China. · School of Artificial Intelligence, University of Chinese Academy of Sciences, 1 Yanqihu East Road, Beijing, 101408, Beijing, China. · PeopleAI, Inc., 68 Zhichun Road, Beijing, 100098, Beijing, China. +1

  17. You Only Erase Once: Erasing Anything without Bringing Unexpected Content

    Mar 29, 2026Yixing Zhu, Qing Zhang, Wenju Xu +1Object RemovalDiffusion-Based Image Editing

    School of Computer Science and Engineering, Sun Yat-sen University, China · Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China · Amazon

  18. DRUM: Diffusion-based Raydrop-aware Unpaired Mapping for Sim2Real LiDAR Segmentation

    Mar 27, 2026Tomoya Miyawaki, Kazuto Nakashima, Yumi Iwashita +1Synthetic-to-Real Domain Adaptation3D Semantic Segmentation

    Graduate School of Information Science and Electrical Engineering, Kyushu University, Japan. · Faculty of Information Science and Electrical Engineering, Kyushu University, Japan. · Jet Propulsion Laboratory, California Institute of Technology, USA.

  19. InstaVSR: Taming Diffusion for Efficient and Temporally Consistent Video Super-Resolution

    Mar 27, 2026Jintong Hu, Bin Chen, Zhenyu Hu +3Video Super-ResolutionDiffusion Models

    Insta360 Research · Peking University · Wuhan University

  20. Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells

    Mar 26, 2026Han Zhang, Guo-Hua Yuan, Chaohao Yuan +6Single-Cell Perturbation ModelingSingle-Cell Transcriptomics

    DAMO Academy, Alibaba Group

  21. Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration

    Mar 25, 2026Danil Tokhchukov, Aysel Mirzoeva, Andrey Kuznetsov +1Diffusion TransformerT2I Diffusion Models

    MSU · FusionBrain Lab, AXXX

  22. A-SelecT: Automatic Timestep Selection for Diffusion Transformer Representation Learning

    Mar 25, 2026Changyu Liu, James Chenhao Liang, Wenhao Yang +6Visual Representation LearningDiffusion Models

    University of Missouri–Kansas City · U. S. Naval Research Laboratory · Lamar University +5

  23. Polynomial Speedup in Diffusion Models with the Multilevel Euler-Maruyama Method

    Mar 25, 2026Arthur JacotDiffusion Model Inference AccelerationDiffusion Sampling

  24. Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning

    Mar 25, 2026Ido Sobol, Kihyuk Sohn, Yoav Blum +4Multi-View Image SynthesisImage Generation

    Technion · Meta AI

  25. LGTM: Training-Free Light-Guided Text-to-Image Diffusion Model via Initial Noise Manipulation

    Mar 25, 2026Ryugo Morita, Stanislav Frolov, Brian Bernhard Moser +3Controllable Image GenerationT2I Diffusion Models

    RPTU Kaiserslautern-Landau & DFKI GmbH, Kaiserslautern, Germany · Faculty of Science and Engineering, Hosei University, Tokyo, Japan

  26. HAM: A Training-Free Style Transfer Approach via Heterogeneous Attention Modulation for Diffusion Models

    Mar 25, 2026Yeqi He, Liang Li, Zhiwen Yang +3Image Style TransferAttention Control in Diffusion Models

    Hangzhou Dianzi University · Institute of Computing Technology, Chinese Academy of Sciences · Macao Polytechnic University

  27. Can We Change "Stroke Size" to Simplify Flow Matching?

    Mar 25, 2026Yunwei Bai, Ying Kiat Tan, Tsuhan ChenDiffusion Models

    National University of Singapore

  28. Manifold Generalization Provably Proceeds Memorization in Diffusion Models

    Mar 24, 2026Zebang Shen, Ya-Ping Hsieh, Niao HeDiffusion ModelsMemorization in Generative Models

    ETH Zurich

  29. CDMT-EHR: A Continuous-Time Diffusion Framework for Generating Mixed-Type Time-Series Electronic Health Records

    Mar 24, 2026Shaonan Liu, Yuichiro Iwashita, Soichiro Nakako +2Synthetic Data GenerationDiffusion Models

    Department of Core Informatics, Graduate School of Informatics, Osaka Metropolitan University, Sakai, Osaka 599-8531, Japan · Smart Data & Knowledge Services Department, German Research Center for Artificial Intelligence (DFKI GmbH), 67663 Kaiserslautern, Germany · Department of Computer Science, RPTU University Kaiserslautern-Landau, 67663 Kaiserslautern, Germany +1

  30. FG-Portrait: 3D Flow Guided Editable Portrait Animation

    Mar 24, 2026Yating Xu, Yunqi Miao, Evangelos Ververas +2Video GenerationDiffusion Models

    National University of Singapore · University of Warwick · Imperial College London +1