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.

Geometry-Aware Dataset Condensation for Diffusion Model Training
Jun 4, 2026Xiao Cui, Yulei Qin, Mo Zhu +3Dataset Distillation Dataset Condensation
University of Science and Technology of China · Independent Researcher · Zhejiang University +1
TabSODA: Tabular Diffusion based Imputation with Skip Pattern Detection and Ordinal Awareness
Jun 3, 2026Yuyu Chen, Taehyo Kim, Hai Shu +1Incomplete Data Imputation Learning with Missing Data
Department of Biostatistics NYU School of Global Public Health
Learning What Not to Impute: An Uncertainty-Aware Diffusion Framework for Meaningful Missingness
Jun 3, 2026Lixing Zhang, Yidong Ouyang, Weifu Li +3Incomplete Data Imputation Learning with Missing Data
University of Minnesota · University of California, Los Angeles · Carnegie Mellon University
Crafting Your Evolving Dreams: Concept-Incremental Versatile Customization
Jun 3, 2026Jiahua Dong, Wenqi Liang, Hongliu Li +7T2I Generation Low-Rank Adaptation
Shanghai Jiao Tong University, Shanghai, China
HyFAD: Hybrid Time-Frequency Diffusion with Frequency-Aware Embedding for Time Series Imputation
Jun 3, 2026Hongfan Gao, Wangmeng Shen, Bin Yang +1Frequency-Domain Time Series Modeling Time Series Imputation
School of Data Science and Engineering East China Normal University
Efficient and Training-Free Single-Image Diffusion Models
Jun 3, 2026Haojun Qiu, Kiriakos N. Kutulakos, David B. LindellImage Generation Diffusion-Based Image Generation
Department of Computer Science, University of Toronto · Vector Institute
PatchScene: Patch-based Voxel Diffusion for Large-Scale Scene Completion
Jun 2, 2026Qingdong Xu, Jiajun Zhu, Shilin Zhu +43D Reconstruction Autonomous Driving Perception
1MEGVII Technology · 2Qianli Technology · 4Northeastern University, China +2
DiverAge: Reliable Pluralistic Face Aging with Cross-Age Identity Relation Guidance
Jun 2, 2026Yueying Zou, Peipei Li, Qianrui Teng +2Image Generation Diffusion Autoencoder
School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China · School of Computer Science, University of California, Santa Barbara, USA
Bionic Human-Motion Style Transfer for Physically Executable Whole-Body Control of Humanoid Robots
Jun 2, 2026Tianchen Huang, Mingkuan Zhao, Yang Gao +8Humanoid Robot Control Human Motion Generation
Institute of Humanoid Robots, Department of Precision Machinery and Precision Instrumentation, University of Science and Technology of China, Hefei, Anhui, 230026, China. · School of Computer Science and Technology, Faculty of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi, 710049, China. · School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, 730000, China.
Flicker-DDPM: Accelerating Denoising Diffusion via 1/f Colored Noise Injection
Jun 2, 2026KeXiang Mao, FanCheng LiFew-Step Diffusion Sampling Diffusion Model Acceleration
School of Physics and Technology, Wuhan University, Wuhan 430072, China · Hongyi Honor College, Wuhan University, Wuhan 430072, China
AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking
Jun 2, 2026Jungkyu Kim, Taeyoung Park, Kibok LeeLearning with Missing Data Tabular Diffusion Models
Department of Statistics and Data Science, Yonsei University, South Korea.
Not All Points Are Equal: Uncertainty-Aware 4D LiDAR Scene Synthesis
Jun 1, 2026Xiang Xu, Alan Liang, Youquan Liu +53D Scene Generation Generative Modeling
1NUAA · 2NUS · 3FDU +4
Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior
Jun 1, 2026Xiang Li, Dianbo Liu, Kenji KawaguchiDiffusion Model Sampling Image Generation
1National University of Singapore.
BlockGen: Flexible Blockwise Sequence Modeling with Hybrid Samplers
Jun 1, 2026Justin Deschenaux, Caglar GulcehreMasked Diffusion Models Diffusion Sampling
EPFL Lausanne, Switzerland · EPFL, Lausanne, Switzerland · Microsoft AI
Error Bounds for a Diffusion Model-Based Drift Estimator
Jun 1, 2026Ioar Casado-Telletxea, Omar RivasplataParameter Estimation Stochastic Differential Equations
Basque Center for Applied Mathematics (BCAM) · Bilbao, Spain · Centre for AI Fundamentals & Department of Computer Science +1
Normality-Preserving Continual Industrial Anomaly Detection via Orthogonal LoRA Banks
Jun 1, 2026Weibai Fang, Haijun Che, Feiyang Ren +1Industrial Anomaly Detection Anomaly Localization
The Lie We Tell: Correcting the Euclidean Fallacy in Vision Language Action Policies via Score Matching on Tangent Space
Jun 1, 2026Bing-Cheng Chuang, I-Hsuan Chu, Bor-Jiun Lin +3Lie Group Methods Robotic Manipulation
Department of Computer Science and Information Engineering & Artificial Intelligence Center of Research Excellence, National Taiwan University, Taipei, Taiwan · Institute of Artificial Intelligence Innovation, National Yang Ming Chiao Tung University, Hsinchu, Taiwan · Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan.
Self-Regulating Annealing in Heavy-Tailed Diffusion Models
Jun 1, 2026Keito Wakatsuki, Hideaki ShimazakiStochastic Differential Equations Diffusion Sampling
Graduate School of Informatics Kyoto University, Kyoto, Japan
E4GEN: Event-level Explainable Extreme-Enhanced Time-series Generation
Jun 1, 2026Lin Jiang, Dahai Yu, Ximiao Li +1Time Series Generation Generative Modeling
Florida State University
Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compression
Jun 1, 2026Hao Wei, Yanhui Zhou, Chenyang Ge +2Learned Image Compression Diffusion Models
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an 710049, China · School of Information and Telecommunication, Xi’an Jiaotong University, Xi’an 710049, China · Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Crawley, WA 6009, Australia
Splatshot: 3D Face Avatar Generation from a Single Unconstrained Photo
May 31, 2026Hao Liang, Zhixuan Ge, Soumendu Majee +33D Gaussian Splatting 3D Asset Generation
Rice University Houston, TX 77005 · Samsung Research America Plano, TX 75023
Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation
May 31, 2026Ziyue Lin, Jiahe Hou, Hongyu Xia +6Diffusion Model Alignment Image-to-Image Translation
1The University of Hong Kong · 2Shenyang Institute of Automation, Chinese Academy of Sciences · 3The Chinese University of Hong Kong +1
GraspGen-X: Cross-Embodiment 6-DOF Diffusion-based Grasping
May 31, 2026Beining Han, Yu-Wei Chao, Erwin Coumans +5Robotic Grasping Generalization in Robotic Manipulation
1NVIDIA · 2Princeton University
Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning
May 30, 2026Byoungwoo Park, Utkarsh A. Mishra, Jaemoo Choi +2Diffusion-Based Planning Long-Horizon Video Generation
KAIST
Generative Diffusion Priors for 3D Mapping of the Dark Universe
May 30, 2026Brandon Zhao, Diana Scognamiglio, Olivier Doré +13D Reconstruction Bayesian Inverse Problems
Department of Computing and Mathematical Sciences, California Institute of Technology · Jet Propulsion Laboratory, California Institute of Technology · Department of Physics, Duke University +1
Manifold Diffusion for Structure Generation of Transition Metal Complexes
May 30, 2026Luca Schaufelberger, Kjell Jorner3D Molecular Generation Molecular Generation
Institute of Chemical and Bioengineering, Department of Chemistry and Applied Biosciences, ETH Zurich. · NCCR Catalysis, Switzerland.
Score-Control for Hallucination Reduction in Diffusion Models
May 29, 2026Mahesh Bhosale, Naresh Kumar Devulapally, Abdul Wasi +3Score Matching Diffusion-Based Image Generation
University at Buffalo Buffalo, NY, USA
Adaptive Order Policies for Masked Diffusion
May 29, 2026Jama Hussein Mohamud, Mohsin Hasan, Mirco Ravanelli +1Masked Diffusion Models Diffusion Model Sampling
Université de Montréal · Mila · Concordia University +1
KLIP: localized distribution shift detection via KL-divergence with diffusion priors in Inverse Problems
May 29, 2026Alireza Kheirandish, Jihoon Hong, Sara Fridovich-KeilDiffusion-Based OOD Detection Distribution Shift Detection
Georgia Institute of Technology
TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation
May 29, 2026Ruotong Liao, Guowen Huang, Qing Cheng +6Diffusion Transformer T2V Generation
Ludwig Maximilian University of Munich · MCML · Technical University of Munich +2

Jun 4, 2026J/K move · Enter open · S save

Geometry-Aware Dataset Condensation for Diffusion Model Training

Xiao Cui, Yulei Qin, Mo Zhu, Wengang Zhou+2

University of Science and Technology of China · Independent Researcher · Zhejiang University+1

Dataset Distillation Dataset Condensation Diffusion Models

Open paper AskPDF arXiv

Dataset condensation aims to construct compact datasets from real data via synthesis or selection. However, existing approaches are ill-suited for diffusion model training: synthetic data generation often yields low-fidelity samples unsuitable for authentic modeling, while real subset selection typically fails to preserve the distributional geometry required by diffusion likelihood objectives. To address this, we propose to reformulate real subset selection as a geometry-aware distribution alignment problem. By incorporating one-sided partial optimal transport, our method selectively aligns a compact subset with the full data distribution while allowing unmatched mass in low-density regions, ensuring the preserved geometric structure necessary for effective diffusion model training. To further ensure distributional fidelity, we complement geometric alignment with lightweight feature-statistics and semantic consistency regularization. An efficient two-stage discrete optimization strategy is proposed to achieve this alignment objective. Extensive experiments across diffusion variants, subset sizes, image resolutions, and training rounds show that our method achieves superior fidelity and distributional coverage in diffusion model training. Codes are available at https://github.com/2018cx/GADC.