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.

Rethinking the Diffusion Model from a Langevin Perspective
Apr 12, 2026Candi Zheng, Yuan LanDiffusion Models
Department of Mathematics, The Hong Kong University of Science and Technology
Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs
Apr 11, 2026Hongkang Li, Hancheng Min, Rene VidalDiffusion Models Diffusion-Based Denoising
Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, USA · Institute of Natural Sciences & School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai, China
FREE-Switch: Frequency-based Dynamic LoRA Switch for Style Transfer
Apr 11, 2026Shenghe Zheng, Minyu Zhang, Tianhao Liu +1Diffusion-Based Image Generation Diffusion Models
Harbin Institute of Technology
Diffusion Denoiser Achievable Analysis for Finite Blocklength Unsourced Random Access
Apr 10, 2026Yuming Han, Yuxin LongDiffusion-Based Denoising Diffusion Models
Texas A&M University, Department of ECE, College Station, TX 77843, USA · University of Leeds, Institute for Transport Studies, Leeds, LS2 9JT, UK
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
Detecting Diffusion-generated Images via Dynamic Assembly Forests
Apr 10, 2026Mengxin Fu, Yuezun LiAI-Generated Image Detection Diffusion Models
School of Computer Science and Technology, Ocean University of China
Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios
Apr 10, 2026Yu Shi, Yu Liu, Zhong-Cheng Wu +3Multi-Source Image Fusion Diffusion Models
Department of Biomedical Engineering, Hefei University of Technology · Faculty of Information Engineering and Automation, Kunming University of Science and Technology · School of Information Science and Technology, University of Science and Technology of China
What Matters in Virtual Try-Off? Dual-UNet Diffusion Model For Garment Reconstruction
Apr 9, 2026Loc-Phat Truong, Meysam Madadi, Sergio EscaleraDiffusion Models Diffusion-Based Image Generation
Computer Vision Center, Spain · Universitat de Barcelona, Spain
Bias-Constrained Diffusion Schedules for PDE Emulations: Reconstruction Error Minimization and Efficient Unrolled Training
Apr 9, 2026Constantin Le Cleï, Nils Thuerey, Xiaoxiang ZhuDiffusion Models Autoregressive Diffusion
Technical University of Munich, Munich, Germany.
PrivFedTalk: Privacy-Aware Federated Diffusion with Identity-Stable Adapters for Personalized Talking-Head Generation
Apr 9, 2026Soumya Mazumdar, Vineet Kumar Rakesh, Tapas SamantaTalking Head Generation Federated Learning
Department of Computer Science and Business Systems Gargi Memorial Institute of Technology Affiliated to Maulana Abul Kalam Azad University of Technology Balarampur, Mouza Beralia, Baruipur, Kolkata 700144, West Bengal, India · Engineering Sciences, Homi Bhabha National Institute Anushaktinagar, Mumbai, Maharashtra 400094, India · Computer and Informatics Group / Radioactive Ion Beam Facilities Group Variable Energy Cyclotron Centre 1/AF, Bidhannagar, Kolkata 700064, West Bengal, India
Beyond the Autoregressive Horizon: A Comprehensive Survey of Diffusion Models, World Modelling, and State Space Models for Code
Apr 9, 2026Kishan Maharaj, Ashita Saxena, Srikanth TamilselvamCode World Models LLM Code Generation
IBM
FlowGuard: Towards Lightweight In-Generation Safety Detection for Diffusion Models via Linear Latent Decoding
Apr 9, 2026Jinghan Yang, Yihe Fan, Xudong Pan +1Diffusion Models Latent Diffusion Models
Fudan University, Shanghai, China · Fudan University, Shanghai Innovation Institute, Shanghai, China
Monocular Depth Estimation From the Perspective of Feature Restoration: A Diffusion Enhanced Depth Restoration Approach
Apr 9, 2026Huibin Bai, Shuai Li, Hanxiao Zhai +6Depth Estimation Monocular Depth Estimation
School of Software, Shandong University, Jinan 250100, China · Shandong University-WeiHai Research Institute of Industrial Technology, Weihai 264209, China · School of Control Science and Engineering, Shandong University, Jinan, China +4
Score Shocks: The Burgers Equation Structure of Diffusion Generative Models
Apr 8, 2026Krisanu SarkarDiffusion Models Score-Based Generative Modeling
Indian Institute of Technology Bombay, Mumbai, India
A Noise Constrained Diffusion (NC-Diffusion) Framework for High Fidelity Image Compression
Apr 8, 2026Zhenyu Du, Yanbo Gao, Shuai Li +3Learned Image Compression Generative Image Compression
Shandong University, Jinan, China · University of Electronic Science and Technology of China, Sichuan, China
Evaluation as Evolution: Transforming Adversarial Diffusion into Closed-Loop Curricula for Autonomous Vehicles
Apr 8, 2026Yicheng Guo, Jiaqi Liu, Chengkai Xu +2Autonomous Driving Safety Evaluation Adversarial Scenario Generation
College of Transportation, Tongji University, Shanghai 201804, China · Department of Computer Science, University of North Carolina at Chapel Hill, United States
Improving Controllable Generation: Faster Training and Better Performance via $x_0$ -Supervision
Apr 7, 2026Amadou S. Sangare, Adrien Maglo, Mohamed Chaouch +1Controllable Image Generation Conditional Diffusion Models
Université Paris-Saclay, CEA, List, F-91120, Palaiseau, France
Cross-Resolution Diffusion Models via Network Pruning
Apr 7, 2026Jiaxuan Ren, Junhan Zhu, Huan WangDiffusion Model Pruning Image Generation
University of Electronic Science and Technology of China · Westlake University
Human Interaction-Aware 3D Reconstruction from a Single Image
Apr 7, 2026Gwanghyun Kim, Junghun James Kim, Suh Yoon Jeon +23D Human Reconstruction Single-View 3D Reconstruction
Dept. of Electrical and Computer Engineering, Seoul National University, Republic of Korea · IPAI, Seoul National University, Republic of Korea · INMC, Seoul National University, Republic of Korea
Extending Tabular Denoising Diffusion Probabilistic Models for Time-Series Data Generation
Apr 6, 2026Umang Dobhal, Christina Garcia, Sozo InoueTime Series Generation Tabular Diffusion Models
OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models
Apr 6, 2026Ali Aliev, Kamil Garifullin, Nikolay Yudin +5Model Merging Diffusion Model Adaptation
HSE University · FusionBrain Lab · AXXX
Graph Signal Diffusion Models for Wireless Resource Allocation
Apr 6, 2026Yigit Berkay Uslu, Samar Hadou, Shirin Saeedi Bidokhti +1Wireless Resource Allocation Diffusion Policy
Dept. of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA
Simultaneous Dual-View Mammogram Synthesis Using Denoising Diffusion Probabilistic Models
Apr 6, 2026Jorge Alberto Garza-Abdala, Gerardo A. Fumagal-González, Eduardo de Avila-Armenta +5Multi-View Image Synthesis Medical Image Synthesis
Tecnologico de Monterrey, School of Engineering and Sciences, Monterrey, Mexico · School of Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile · Tecnologico de Monterrey, School of Medicine and Health Sciences, Monterrey, Mexico
Align Your Structures: Generating Trajectories with Structure Pretraining for Molecular Dynamics
Apr 5, 2026Aniketh Iyengar, Jiaqi Han, Pengwei Sun +3Molecular Dynamics Simulation 3D Molecular Generation
Stanford University · Lambda, Inc
ML-based approach to classification and generation of structured light propagation in turbulent media
Apr 4, 2026Aokun Wang, Anjali Nair, Zhongjian Wang +1Synthetic Data Augmentation Conditional Diffusion Models
Division of Mathematical Sciences, Nanyang Technological University, 21 Nanyang Link, 637371 Singapore · Committee on Computational and Applied Mathematics, University of Chicago, Chicago, IL 60637 USA · Departments of Statistics and Mathematics, University of Chicago, Chicago, IL 60637 USA
CountsDiff: A Diffusion Model on the Natural Numbers for Generation and Imputation of Count-Based Data
Apr 4, 2026Renzo G. Soatto, Anders Hoel, Greycen Ren +5Diffusion Models Synthetic Data Generation
Massachusetts Institute of Technology (MIT), Cambridge, MA, USA · Laboratory for Information and Decision Systems (LIDS), MIT, Cambridge, MA, USA · Eric and Wendy Schmidt Center, Broad Institute, Cambridge, MA, USA +1
StrADiff: A Structured Source-Wise Adaptive Diffusion Framework for Linear and Nonlinear Blind Source Separation
Apr 4, 2026Yuan-Hao WeiDiffusion Models
DiffSparse: Accelerating Diffusion Transformers with Learned Token Sparsity
Apr 4, 2026Haowei Zhu, Ji Liu, Ziqiong Liu +4Diffusion Model Inference Acceleration Diffusion Models
Advanced Micro Devices, Inc. · Tsinghua University · BNRist
NeuralLVC: Neural Lossless Video Compression via Masked Diffusion with Temporal Conditioning
Apr 3, 2026Tiberio Uricchio, Marco BertiniMasked Diffusion Models Neural Video Compression
University of Pisa · Pisa, Italy · Università degli Studi di Firenze +1
Understanding Latent Diffusability via Fisher Geometry
Apr 3, 2026Jing Gu, Morteza Mardani, Wonjun Lee +2Information Geometry Neural Representation Geometry
School of Mathematics, University of Minnesota · NVIDIA · Department of Mathematics, The Ohio State University +1

Apr 12, 2026J/K move · Enter open · S save

Rethinking the Diffusion Model from a Langevin Perspective

Candi Zheng, Yuan Lan

Department of Mathematics, The Hong Kong University of Science and Technology

Diffusion Models

Open paper AskPDF arXiv

Diffusion models are often introduced from multiple perspectives, such as VAEs, score matching, or flow matching, accompanied by dense and technically demanding mathematics that can be difficult for beginners to grasp. One classic question is: how does the reverse process invert the forward process to generate data from pure noise? This article systematically organizes the diffusion model from a fresh Langevin perspective, offering a simpler, clearer, and more intuitive answer. We also address the following questions: how can ODE-based and SDE-based diffusion models be unified under a single framework? Why are diffusion models theoretically superior to ordinary VAEs? Why is flow matching not fundamentally simpler than denoising or score matching, but equivalent under maximum-likelihood? We demonstrate that the Langevin perspective offers clear and straightforward answers to these questions, bridging existing interpretations of diffusion models, showing how different formulations can be converted into one another within a common framework, and offering pedagogical value for both learners and experienced researchers seeking deeper intuition.