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.

MoDDiT: Simple Token Routing in Diffusion Transformers
Oct 20, 2026Jarek Liesen, Matthew T. Jackson, Benjamin Ellis +2Diffusion Transformer Adaptive Computation for Diffusion Models
British Open-ended Learning and Discovery
Detection of Memorization in Diffusion Models Through Thermodynamic Singularity
Oct 20, 2026Iljung Kim, Kangwoo Park, Yung-Kyun Noh +1Memorization in Generative Models Diffusion Models
Hanyang University Seoul 04763, Rep. of Korea. · Cornell Tech New York, NY 10044, USA
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
RECAP: Reciprocal Sparse Attention and Hierarchical Caching for Efficient Video Diffusion
Oct 19, 2026Tiange Xu, Kai Liu, Linghe Kong +1Video Diffusion Models Diffusion Model Inference Acceleration
University of Cambridge · Shanghai Jiao Tong University
SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolation
Oct 19, 2026Yanjin He, Cuifeng Shen, Wanzhou Lei +5Diffusion Models Diffusion Model Guidance
University of Michigan, Ann Arbor · Alibaba Group · University of California, Berkeley +1
Hihaze: One-Step Diffusion for High-Resolution Real-World Image Dehazing
Oct 19, 2026Zheng Chen, Yuchen Huang, Xiaoyang Liu +3Image Dehazing Diffusion Models for Image Restoration
Shanghai Jiao Tong University
PoSTCache: From Forecasting to Postdictive Smoothing for Revisable Diffusion Caching
Oct 19, 2026Liwei Lan, Hui Chen, Jungong Han +1Diffusion Model Caching Diffusion Model Inference Acceleration
School of Software, Tsinghua University · BNRist, Tsinghua University · Department of Automation, Tsinghua University
T(R,O) Grasp++: Cross-Embodiment Dexterous Grasping in Cluttered Environments at Scale
Oct 18, 2026Xin Fei, Zhixuan Xu, Huaicong Fang +5Robotic Grasping Cross-Embodiment Robot Learning
Department of Computer Science, National University of Singapore · RoboScience · College of Control Science and Engineering, Zhejiang University, China +2
PolarVis: A Dataset and Diffusion Framework for RGB-to-Polarization Perception in Adverse Driving Scenes
Oct 18, 2026Ruilin Huang, Jue Wang, Zhen Tian +2Polarimetric Imaging Image-to-Image Translation
School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen 518107, China · Department of Electrical Engineering, Carleton University, Ottawa, Ontario K1S 5B6, Canada
LiftDiff: Guided Discrete Diffusion for Quantum Code Construction
Oct 18, 2026Yotam Peled, Eliya NachmaniQuantum Error Correction Quantum LDPC Codes
School of Electrical And Computer Engineering, Ben-Gurion University of the Negev, Israel
Rethinking the design space of Vanilla Pixel Diffusion Transformers
Oct 16, 2026Soumik Mukhopadhyay, Long Mai, Abhinav Shrivastava +1Diffusion-Based Image Generation Diffusion Models
University of Maryland, College Park · Adobe Research
Information Estimation with Discrete Diffusion
Oct 16, 2026Alberto Foresti, Giulio Franzese, Pietro MichiardiMutual Information Estimation Diffusion Models
Department of Data Science, EURECOM, 450 Route des Chappes, 06410 Biot, France
Data-Efficient Classifier Pretraining Through Diffusion Models
Oct 16, 2026Qinyu Li, Yee Whye Teh, Chris Holmes +1Data-Efficient Learning Self-Supervised Pre-Training
Department of Statistics, University of Oxford · Faculty of Medicine and Health Technology, Tampere University · Tampere Institute for Advanced Study, Tampere University
Large Diffusion Models Need More Than EMA
Oct 16, 2026Chuyu Hu, Huanran Chen, Shitong Shao +1Deep Learning Optimization Diffusion Models
Tsinghua University · Shanghai Qi Zhi Institute · The Hong Kong University of Science and Technology
HilbertGen-3D:Hilbert--Multifractal Conditioning for Topology-Aware 3D Generation
Oct 15, 2026Ziyi Zhang, Shixuan Li, Yorie Nakahira +23D Shape Generation Point Cloud Generation
Department of Electrical and Computer Engineering, Carnegie Mellon University · Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California
Routing Policy Optimization for Online Diffusion Reinforcement Learning
Oct 15, 2026Qiuhong Shen, Yiding Yang, Yuxin Zhang +8RL for Image Generation RL for Diffusion Models
National University of Singapore · ByteDance
Reinforcement Learning-driven Diffusion Models: Language, Vision, and Beyond
Oct 15, 2026Zhiyuan Ma, Jiabao Wei, Tianyu Wang +21RL for Diffusion Models RL for Generative Models
Huazhong University of Science and Technology · Beijing Institute of Technology · Tsinghua University +9
Score Mismatch and Set-Constrained Sampling in Zero-Shot Conditional Discrete Diffusion
Oct 15, 2026Renxiang Huang, Yuchen Liang, Yingbin Liang +2Diffusion Models Diffusion Sampling
Department of Electrical and Computer Engineering, University of California, Davis, Davis, CA, 95616, USA · Luddy School of Informatics, Computing, and Engineering, Indiana University Indianapolis, Indianapolis, IN, 46202, USA · Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH, 43210, USA
EigDiff: Eigensample Diffusion - or how to significantly reduce training dataset size with marginal performance variation?
Oct 14, 2026Andrei Jarca, Vlad Hondru, Florinel-Alin Croitoru +1Diffusion Models Training Data Selection
University of Bucharest, Romania
Two-Stage Score Estimation for Group-Specific Diffusion Models
Oct 14, 2026Huitao Yang, Oscar Hernan Madrid PadillaDiffusion Models Score-Based Generative Modeling
University of California, Los Angeles
Purify Before You Align: Improving Representation Alignment for Diffusion Models
Oct 14, 2026Yingheng Wang, Yaoqiang Li, Yaqin Wu +4Diffusion Model Alignment Diffusion-Based Image Generation
Cornell University · Independent researcher. · University of Pennsylvania
Mixed Poisson diffusion models and application to posterior sampling
Oct 14, 2026Thibaut Pellerin, Alain Durmus, Elinor Berger +1Diffusion Models Diffusion Posterior Sampling
CMAP, CNRS, École polytechnique, Institut Polytechnique de Paris, Palaiseau, France · Université Paris-Saclay, CEA, List, F-91120 Palaiseau, France
Value-Informed Schedule Trimming for Accelerated Sequential Monte Carlo Guidance in Discrete Diffusion
Oct 14, 2026Jaehyeon Kim, Ziseok Lee, Siyoung Choi +1Inference-Time Guidance Diffusion Models
Seoul National University
From Global to Tail Convergence: Dynamics of $α$ -Stable Score-Based Generative Models
Oct 14, 2026Ianis Hammani, Claire BoyerScore-Based Generative Modeling Diffusion Models
ENS Paris Saclay, LMO · LMO, IUF
Annealed Lévy Diffusion via Gaussian Surrogate Reverse Dynamics
Oct 14, 2026Yuling Jiao, Lican Kang, Jerry Zhijian Yang +2Diffusion Sampling Diffusion Models
School of Artificial Intelligence, Wuhan University, Wuhan, Hubei 430072, China. · Institute for Math and AI, Hubei Key Laboratory of Computational Science, and School of Artificial Intelligence, Wuhan University, Wuhan, 430072, China. · School of Mathematics and Statistics, Wuhan University, Wuhan, Hubei 430072, China.
DeBoneDiT: Depth-Driven Conditional Bridge Diffusion Transformers for Bone Suppression in Chest X-Ray Images
Oct 14, 2026Yifei Sun, Fenglei Fan, Junhao Jia +4Medical Imaging Diffusion Models for Image Restoration
Zhejiang University · Hangzhou Dianzi University · City University of Hong Kong +2
Decoupled Drift-Diffusion World Models for Consistent Future Frame Prediction
Oct 13, 2026Anton Arapin, Aditya Singh, Yixin Wang +2Aleatoric Uncertainty Action-Conditioned World Models
University of Michigan · NVIDIA
Loss Curvature as a Sampling-Free Proxy for Memorization in Diffusion Models
Oct 13, 2026Shashank Sule, Xinyue Yu, Boonam Shin +3Memorization in Generative Models Diffusion Models
Department of Mathematics, University of California, Los Angeles, CA 90095, USA. · Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA.
Discrete Diffusion Models are Minimax Optimal Under Sparsity
Oct 13, 2026Luca Blunda, Tyler Farghly, Umut Simsekli +1Diffusion Models Minimax Estimation
INRIA - École Normale Supérieure - PSL Research University - CNRS, France · École Polytechnique - CMAP - IP Paris, France
Discovering Undisclosed Concepts in LoRA Adapters for Diffusion-Based AIGC Models
Oct 13, 2026Yupeng Qiu, Han Fang, Dhananjai Sharma +1T2I Diffusion Models Diffusion Models
National University of Singapore · University of Science and Technology of China

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

MoDDiT: Simple Token Routing in Diffusion Transformers

Jarek Liesen, Matthew T. Jackson, Benjamin Ellis, Shimon Whiteson+1

British Open-ended Learning and Discovery

Diffusion Transformer Adaptive Computation for Diffusion Models Diffusion Models Diffusion-Based Image Generation Video Diffusion Models

Open paper AskPDF arXiv

Real-time video generation, interactive world models, and on-device image synthesis are almost a reality. Diffusion Transformers (DiT) achieve excellent sample quality, shifting the bottleneck to the throughput of the models themselves. Natural images are inherently sparse, as large portions of an image are often background, contribute little to the scene content, and are easy to denoise. DiTs fail to exploit this sparsity, as they process image tokens statically and uniformly. We propose MoDDiT, a simple architecture modification that learns to route tokens through both MLP and self-attention operations. By routing tokens through both blocks independently, MoDDiT allows for dynamic compute allocation in MLPs that varies across tokens, images, and denoising timesteps. Using MoDDiT to train image generation models from scratch significantly reduces computational costs of training and inference, processing as few as 12.5% of the tokens. By increasing sparsity and model depth, MoDDiT reduces costs and improves generation performance over unrouted baselines. The learned allocation is interpretable, revealing how computation varies with visual content and noise level. We also use MoDDiT to train video generation models, where allocation correlates with motion, and to distill a dense bidirectional video model into a sparse autoregressive student.