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.

Flow Sampling: Learning to Sample from Unnormalized Densities via Denoising Conditional Processes
May 5, 2026Aaron Havens, Brian Karrer, Neta ShaulSampling from Unnormalized Distributions Diffusion Sampling
FAIR at Meta · Weizmann Institute of Science
Diffusion Masked Pretraining for Dynamic Point Cloud
May 5, 2026Zhuoyue Zhang, Yiding Sun, Haozhe Cheng +4Self-Supervised Pre-Training Point Cloud Learning
School of Software Engineering, Xi’an Jiaotong University, Xi’an, China · School of Artificial Intelligence and Robotics, Hunan University, Changsha, China · Department of Computer Science and Software Engineering, University of Western Australia, Perth, Australia
Stochastic Schrödinger Diffusion Models for Pure-State Ensemble Generation
May 5, 2026Jian Xu, Wei Chen, Shigui Li +5Quantum Generative Modeling Quantum State Preparation
1RIKEN iTHEMS · 2RIKEN AIP · 3South China University of Technology +2
GRIFDIR: Graph Resolution-Invariant FEM Diffusion Models in Function Spaces over Irregular Domains
May 5, 2026James Rowbottom, Elizabeth L. Baker, Nick Huang +3Graph Neural Operators Finite Element Method
Department of Applied Mathematics and Theoretical Physics, University of Cambridge, UK · Department of Applied Mathematics and Computer Science, Technical University of Denmark, Denmark · Department of Mathematics, Simon Fraser University, Canada +1
ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstruction
May 4, 2026Aoyu Liu, Zhen Liu, Ziyi Wang +3Image Enhancement HDR Imaging
University of Electronic Science and Technology of China
Skipping the Zeros in Diffusion Models for Sparse Data Generation
May 3, 2026Phil Sidney Ostheimer, Mayank Nagda, Andriy Balinskyy +6Synthetic Data Generation Diffusion Model Acceleration
1RPTU University Kaiserslautern-Landau · 2Heidelberg Univer · University of California, Irvine.
NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training
May 2, 2026Haokai Zhao, Da Xing, Hanqun Cao +13Diffusion Models
UNSW · UCL · The University of Chicago +9
Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control
May 2, 2026Jinhao Zhang, Zhexuan Zhou, Huizhe Li +5Visuomotor Policy Learning Diffusion Policy
Harbin Institute of Technology, Shenzhen · Shanghai Jiao Tong University
Unifying Deep Stochastic Processes for Image Enhancement
May 2, 2026Wojciech Kozłowski, Radosław Kuczbański, Kamil Adamczewski +2Image Enhancement Stochastic Differential Equations
Wrocław University of Science and Technology, Wrocław, Poland · Tooploox, Warsaw, Poland
CSGuard: Toward Forgery-Resistant Watermarking in Diffusion Models via Compressed Sensing Constraint
May 2, 2026Jiewei Lai, Lan Zhang, Chen Tang +4Diffusion Model Watermarking Compressed Sensing
University of Science and Technology of China · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center · Lenovo Research
Action Agent: Agentic Video Generation Meets Flow-Constrained Diffusion
May 2, 2026Jeffrin Sam, Nguyen Khang, Yara Mahmoud +2Trajectory Generation Diffusion-Based Planning
Intelligent Space Robotics Laboratory, Skoltech, Bolshoy Boulevard, 30, Moscow 121205, Russia
Scale-Aware Adversarial Analysis: A Diagnostic for Generative AI in Multiscale Complex Systems
May 1, 2026Mengke Zhao, Guang-Xing Li, Duo Xu +1Generative Modeling Generative AI Evaluation
School of Astronomy and Space Science, Nanjing University, 163 Xianlin Avenue, Nanjing 210023, Jiangsu, People’s Republic of China · Key Laboratory of Modern Astronomy and Astrophysics (Nanjing University), Ministry of Education, Nanjing 210023, Jiangsu, People’s Republic of China · South-Western Institute for Astronomy Research, Yunnan University, Kunming 650091, People’s Republic of China +1
GD4: Graph-based Discrete Denoising Diffusion for MIMO Detection
May 1, 2026Qincheng Lu, Sitao Luan, Xiao-Wen ChangDiffusion Model Inference Acceleration Diffusion Models
School of Computer Science McGill University Montreal, Canada · University of Montreal Mila - Quebec AI Institute Montreal, Canada
Trees to Flows and Back: Unifying Decision Trees and Diffusion Models
May 1, 2026Sai Niranjan Ramachandran, Suvrit SraDecision Tree Learning Diffusion Models
School of Computation, Information and Technology, Technical University of Munich, Germany · Munich center for machine learning (MCML)
Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding
May 1, 2026An Huang, Junggab Son, Zuobin XiongAdversarial Attacks Diffusion Models
Department of Computer Science, University of Nevada Las Vegas, Las Vegas, USA.
Binomial flows: Denoising and flow matching for discrete ordinal data
May 1, 2026Yair Shenfeld, Ricardo Baptista, Stefano PeluchettiFlow Matching Flow-Based Generative Modeling
VQ-SAD: Vector Quantized Structure Aware Diffusion For Molecule Generation
May 1, 2026Farshad Noravesh, Reza Haffari, Layki Soon +1Latent Diffusion Models Vector-Quantized Variational Autoencoder
Pose-Aware Diffusion for 3D Generation
May 1, 2026Zihan Zhou, Luxi Chen, Jingzhi Zhou +43D Asset Generation 3D Scene Generation
Gaoling School of AI, Renmin University of China · VCIP, School of Computer Science, Nankai University · THU-Bosch MLCenter, Tsinghua University +1
Noise2Map: End-to-End Diffusion Model for Semantic Segmentation and Change Detection
Apr 30, 2026Ali Shibli, Andrea Nascetti, Yifang BanImage Segmentation Remote Sensing Image Segmentation
Division of Geoinformatics, School of Architecture and Built Environment, KTH Royal Institute of Technology, 11428 Stockholm, Sweden
Generative structure search for efficient and diverse discovery of molecular and crystal structures
Apr 30, 2026Yifang Qin, Yu Shi, Junfu Tan +3Crystal Structure Prediction Crystal Structure Generation
School of Computer Science, Peking University Beijing, 100871, China. · 2Zhongguancun Academy, Beijing, 100094, China. · School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, 30332, Georgia, USA. +1
REVIVE 3D: Refinement via Encoded Voluminous Inflated prior for Volume Enhancement
Apr 30, 2026Hankyeol Lee, Wooyeol Baek, Seongdo Kim +13D Asset Generation 3D Diffusion Models
Yonsei University
CasLayout: Cascaded 3D Layout Diffusion for Indoor Scene Synthesis with Implicit Relation Modeling
Apr 30, 2026Yingrui Wu, Youkang Kong, Mingyang Zhao +33D Spatial Reasoning 3D Scene Generation
MAIS, Institute of Automation, Chinese Academy of Sciences and School of Artificial Intelligence, University of Chinese Academy of Sciences, China · Tsinghua University, China · SKLMS, Academy of Mathematics and Systems Science, Chinese Academy of Sciences and University of Chinese Academy of Sciences, China +1
Language Diffusion Models are Associative Memories Capable of Retrieving Unseen Data
Apr 29, 2026Bao Pham, Mohammed J. Zaki, Luca Ambrogioni +2Memorization in Generative Models Neural Network Memorization
1Rensselaer Polytechnic Institute (RPI) · 2Donders Institute for Brain, Cognition, and Behaviour, Radboud University · 3Dynamical Mind +1
SnapPose3D: Diffusion-Based Single-Frame 2D-to-3D Lifting of Human Poses
Apr 29, 2026Alessandro Simoni, Riccardo Catalini, Davide Di Nucci +63D Human Pose Estimation Diffusion Models
University of Modena and Reggio Emilia (UniMoRe), Italy · Toyota Motor Europe (TME), Brussels, Belgium · Woven by Toyota, Japan
Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models
Apr 29, 2026Zhirong Shen, Rui Huang, Jiacheng Liu +6Diffusion Transformer Diffusion Model Caching
Shanghai Jiao Tong University · University of Electronic Science and Technology of China · Shandong University +2
ACPO: Anchor-Constrained Perceptual Optimization for Diffusion Models with No-Reference Quality Guidance
Apr 29, 2026Yang Yang, Feifan Meng, Han Fang +1Diffusion Model Guidance Diffusion Model Fine-Tuning
School of Electronic and Information Engineering, Anhui University · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center · School of Cyber Science and Technology, University of Science and Technology of China
High-Dimensional Noise to Low-Dimensional Manifolds: A Manifold-Space Diffusion Framework for Degraded Hyperspectral Image Classification
Apr 29, 2026Boxiang Yang, Ning Chen, Xia Yue +6Manifold Learning Hyperspectral Image Classification
Institute of Remote Sensing and Geographic Information System, Peking University, Beijing 100871, China · Beijing Key Laboratory of Spatio-temporal Perception and Urban Resilience, Peking University, Beijing 100871, China · School of Computer Science and Engineering, Central South University, Changsha 410083, China +4
Simple Self-Conditioning Adaptation for Masked Diffusion Models
Apr 28, 2026Michael Cardei, Huu Binh Ta, Ferdinando FiorettoMasked Diffusion Models Diffusion Model Fine-Tuning
University of Virginia
RADD: Retrieval-Anchored Discrete Diffusion for Multi-Modal Knowledge Graph Completion
Apr 28, 2026Guanglin Niu, Bo LiKG Embedding Multimodal KGs
School of Artificial Intelligence, Beihang University
The Thinking Pixel: Recursive Sparse Reasoning in Multimodal Diffusion Latents
Apr 28, 2026Yuwei Sun, Yuxuan Yao, Hui Li +1Diffusion Transformer Conditional Image Generation
Shanghai Academy of AI for Science · Fudan University

May 5, 2026J/K move · Enter open · S save

Flow Sampling: Learning to Sample from Unnormalized Densities via Denoising Conditional Processes

Aaron Havens, Brian Karrer, Neta Shaul

FAIR at Meta · Weizmann Institute of Science

Sampling from Unnormalized Distributions Diffusion Sampling Energy-Based Models Diffusion Models

Open paper AskPDF arXiv

Sampling from unnormalized densities is analogous to the generative modeling problem, but the target distribution is defined by a known energy function instead of data samples. Because evaluating the energy function is often costly, a primary challenge is to learn an efficient sampler. We introduce Flow Sampling, a framework built on diffusion models and flow matching for the data-free setting. Our training objective is conditioned on a noise sample and regresses onto a denoising diffusion drift constructed from the energy function. In contrast, diffusion models' objective is conditioned on a data sample and regresses onto a noising diffusion drift. We utilize the interpolant process to minimize the number of energy function evaluations during training, resulting in an efficient and scalable method for sampling unnormalized densities. Furthermore, our formulation naturally extends to Riemannian manifolds, enabling diffusion-based sampling in geometries beyond Euclidean space. We derive a closed-form formula for the conditional drift on constant curvature manifolds, including hyperspheres and hyperbolic spaces. We evaluate Flow Sampling on synthetic energy benchmarks, small peptides, large-scale amortized molecular conformer generation, and distributions supported on the sphere, demonstrating strong empirical performance.