Diffusion Models

Follow this topic Ask about this topic

Momentum

99 papers in the last four weeks, up 168% on the four weeks before. 1.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 934

All topics

Conditional Diffusion Under Linear Constraints: Langevin Mixing and Information-Theoretic Guarantees
May 6, 2026Ahmad Aghapour, Erhan Bayraktar, Asaf CohenBayesian Inverse Problems Diffusion Models
Department of Mathematics University of Michigan Ann Arbor, MI 48109, USA
D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
May 6, 2026Dengyang Jiang, Xin Jin, Dongyang Liu +9Diffusion Models Supervised Finetuning
1The Hong Kong University of Science and Technology · 2Z-Image Team, Alibaba Group · 4The Chinese University of Hong Kong +1
Computer-Aided Design Generation by Cascaded Discrete Diffusion Model
May 6, 2026Honghu Pan, Xiaoling Luo, Yongyong Chen +2Diffusion Models Diffusion Dynamics
School of Artificial Intelligence and Robotics, Hunan University · College of Computer Science and Software Engineer, Shenzhen University · School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen +1
Local Intrinsic Dimension Unveils Hallucinations in Diffusion Models
May 6, 2026Bartlomiej Sobieski, Matthew Tivnan, Dawid Płudowski +4Diffusion Models Visual Hallucinations
Centre for Credible AI, Warsaw University of Technology · University of Warsaw · Massachusetts General Hospital +1
Deep Dreams Are Made of This: Visualizing Monosemantic Features in Diffusion Models
May 6, 2026Adam Szokalski, Mateusz ModrzejewskiLatent Visual Reasoning Latent Diffusion Model
Institute of Computer Science, Warsaw University of Technology, Warsaw, Poland
Concurrence of Symmetry Breaking and Nonlocality Phase Transitions in Diffusion Models
May 6, 2026Yifan F. Zhang, Fangjun Hu, Guangkuo Liu +2Diffusion Models Phase Transitions
Department of Electrical and Computer Engineering Princeton University Princeton, NJ 08544, USA · QuEra Computing Inc. 1284 Soldiers Field Road, Boston, MA 02135, USA · JILA and Department of Physics University of Colorado Boulder Boulder, CO 80309, USA +1
DiCLIP: Diffusion Model Enhances CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation
May 6, 2026Zhiwei Yang, Pengfei Song, Yucong Meng +3Semantic Segmentation Class Activation Mapping
Academy for Engineering and Technology, Fudan University, Shanghai 200433, China · Shandong Computer Science Center, China · Digital Medical Research Center, School of Basic Medical Science, Fudan University, and also with Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention, Shanghai 200032, China +1
HDFlow: Hierarchical Diffusion-Flow Planning for Long-horizon Tasks
May 6, 2026Nandiraju Gireesh, Yuanliang Ju, Chaoyi Xu +3Diffusion Planning Classical Planning
1Peking University · University of Toronto. · 2Galbot
Towards General Preference Alignment: Diffusion Models at Nash Equilibrium
May 6, 2026Jiaming Hu, Jiamu Bai, Haoyu Wang +2Diffusion Alignment Preference Alignment
Boston University · Penn State University · University at Albany
Beyond Penalization: Diffusion-based Out-of-Distribution Detection and Selective Regularization in Offline Reinforcement Learning
May 6, 2026Qingjun Wang, Hongtu Zhou, Hang Yu +5Out-Of-Distribution Detection Out-Of-Distribution
School of Computer Science and Technology, Tongji University, Shanghai, China · MOE Key Lab of Embedded System and Service Computing, Tongji University, Shanghai, China · Shanghai Innovation Institute
Leveraging Pretrained Language Models as Energy Functions for Glauber Dynamics Text Diffusion
May 5, 2026Tarun Kathuria, Sachin KumarDiffusion Language Models Large Language Model Pretraining
UC Berkeley · Ohio State University
DMGD: Train-Free Dataset Distillation with Semantic-Distribution Matching in Diffusion Models
May 5, 2026Qichao Wang, Yunhong Lu, Hengyuan Cao +2Diffusion-Based Dataset Distillation Dataset Distillation
Zhejiang University · Shanghai Institute for Advanced Study-Zhejiang University · Shanghai Institute for Mathematics and Interdisciplinary Sciences
Tempered Guided Diffusion
May 5, 2026Andreas Makris, Paul Fearnhead, Chris NemethDiffusion Sampling Diffusion Priors
Department of Mathematics and Statistics Lancaster University, UK · Department of Mathematics and Statistics2026 Lancaster University, UK
GRIFDIR: Graph Resolution-Invariant FEM Diffusion Models in Function Spaces over Irregular Domains
May 5, 2026James Rowbottom, Elizabeth L. Baker, Nick Huang +3Diffusion Models Discretization
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
Geometry over Density: Few-Shot Cross-Domain OOD Detection
May 5, 2026Shawn Li, You Qin, Jiate Li +4Out-Of-Distribution Detection Unlabeled Data
University of Southern California · National University of Singapore · Amazon
Refining Compositional Diffusion for Reliable Long-Horizon Planning
May 4, 2026Kyowoon Lee, Yunhao Luo, Anh Tong +1Diffusion Planning Long-Horizon Planning
KAIST · University of Michigan · Korea University +1
Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning
May 4, 2026Rufeng Chen, Zhaofan Zhang, Zhejiang Yang +2Reward Gradients Diffusion Models
1The Hong Kong University of Science and Technology (Guangzhou) · 2Jilin University
TOC-SR: Task-Optimal Compact diffusion for Image Super Resolution
May 4, 2026Sowmya Vajrala, Akshay Bankar, Manjunath Arveti +5Generative Super-Resolution Diffusion Models
Samsung Research Institute Bangalore, India
Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE
May 4, 2026Yangming Shi, Shixiang Zhu, Tao Shen +14Diffusion Models Multimodal Understanding
Mamoda Team, ByteDance
A Hybrid Approach for Closing the Sim2real Appearance Gap in Game Engine Synthetic Datasets
May 4, 2026Stefanos PasiosSynthetic-To-Real Domain Gap Sim-To-Real Gap
independent researcher
CBV: Clean-label Backdoor Attacks on Vision Language Models via Diffusion Models
May 4, 2026Ji Guo, Xiaolong Qin, Cencen Liu +3Clean Label Backdoor Attack Diffusion Models
Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China, China · School of Software Engineering, Chengdu University of Information Technology, China · The Hong Kong University of Science and Technology, China
SlimDiffSR: Toward Lightweight and Efficient Remote Sensing Image Super-Resolution via Diffusion Model Distillation
May 4, 2026Ce Wang, Zhenyu Hu, Wanjie SunHyperspectral Image Super-Resolution Residual Conditional Diffusion Model
School of Remote Sensing and Information Engineering, Wuhan University; Wuhan 430079, China
Skipping the Zeros in Diffusion Models for Sparse Data Generation
May 3, 2026Phil Sidney Ostheimer, Mayank Nagda, Andriy Balinskyy +6Diffusion Models Sparsity
1RPTU University Kaiserslautern-Landau · 2Heidelberg Univer · University of California, Irvine.
SteeringDiffusion: A Bottlenecked Activation Control Interface for Diffusion Models
May 3, 2026Fangzheng Wu, Brian SummaDiffusion Models Controllability
Department of Computer Science Tulane University
NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training
May 2, 2026Haokai Zhao, Da Xing, Hanqun Cao +13Diffusion Models Meta-Learning
UNSW · UCL · The University of Chicago +9
Unifying Deep Stochastic Processes for Image Enhancement
May 2, 2026Wojciech Kozłowski, Radosław Kuczbański, Kamil Adamczewski +2Image Enhancement Diffusion Bridges
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 +4Watermarking Forgeries
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 +2Action Generation Video Agent
Intelligent Space Robotics Laboratory, Skoltech, Bolshoy Boulevard, 30, Moscow 121205, Russia
Phase-map synthesis from magnitude-only MR images using conditional score-based diffusion models with application in training of accelerated MRI reconstruction models
May 2, 2026M. Berk Sahin, Dilek Yalcinkaya, Abolfazl Hashemi +1Magnetic Resonance Imaging Reconstruction Magnetic Resonance Imaging
Purdue University
Faithful Extreme Image Rescaling with Learnable Reversible Transformation and Semantic Priors
May 1, 2026Hao Wei, Yanhui Zhou, Chenyang Ge +2Image Restoration Residual Conditional Diffusion Model
State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University · School of Information and Communications Engineering, Xi’an Jiaotong University · Department of Computer Science and Software Engineering, The University of Western Australia
Colorful-Noise: Training-Free Low-Frequency Noise Manipulation for Color-Based Conditional Image Generation
May 1, 2026Nadav Z. Cohen, Ofir Abramovich, Ariel ShamirText-To-Image Diffusion Models Diffusion Models
Reichman University, Israel
IdentiFace: Multi-Modal Iterative Diffusion Framework for Identifiable Suspect Face Generation in Crime Investigations
May 1, 2026Weichen Liu, Yixin Yang, Changsheng Chen +1Facial Images Identity-Conditioned Latent Diffusion Models
Southeast University · Nanjing, China · Shenzhen MSU-BIT University +1
Trees to Flows and Back: Unifying Decision Trees and Diffusion Models
May 1, 2026Sai Niranjan Ramachandran, Suvrit SraDecision Trees Diffusion Models
School of Computation, Information and Technology, Technical University of Munich, Germany · Munich center for machine learning (MCML)
Fusing Urban Structure and Semantics: A Conditional Diffusion Model for Cross-City OD Matrix Generation
May 1, 2026Bin Chen, Zhuoya Meng, Fang Yang +5Origin Destination Flows Urban Environments
Institute of Intelligent Computing, University of Electronic Science and Technology of China (UESTC), Chengdu, 611731, Sichuan, China · College of Systems Engineering, National University of Defense Technology, Changsha, 410073, Hunan, China · Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China +1
Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding
May 1, 2026An Huang, Junggab Son, Zuobin XiongTimestep Embeddings 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 PeluchettiGenerative Models Diffusion Models
Fast Text-to-Audio Generation with One-Step Sampling via Energy-Scoring and Auxiliary Contextual Representation Distillation
May 1, 2026Kuan-Po Huang, Bo-Ru Lu, Byeonggeun Kim +8Text-To-Audio Autoregressive Diffusion
National Taiwan University · Amazon AGI
When Do Diffusion Models learn to Generate Multiple Objects?
Apr 30, 2026Yujin Jeong, Arnas Uselis, Iro Laina +2Text-To-Image Diffusion Models Diffusion Models
TU Darmstadt & hessian.AI · University of Tübingen · Visual Geometry Group, University of Oxford +1
Consistent Diffusion Language Models
Apr 30, 2026Hasan Amin, Yuan Gao, Yaser Souri +4Diffusion Language Models Diffusion Models
Department of Computer Science, Purdue University · Microsoft
Diffusion-OAMP for Joint Image Compression and Wireless Transmission
Apr 30, 2026Wentao Hou, Yimin Bai, Zelei Luo +2Diffusion Models Signal-To-Noise Ratio
College of Information Science and Electronic Engineering, Zhejiang University, China
Noise2Map: End-to-End Diffusion Model for Semantic Segmentation and Change Detection
Apr 30, 2026Ali Shibli, Andrea Nascetti, Yifang BanChange Detection Semantic Segmentation
Division of Geoinformatics, School of Architecture and Built Environment, KTH Royal Institute of Technology, 11428 Stockholm, Sweden
Probabilistic data quality assessment for structural monitoring data via outlier-resistant conditional diffusion model
Apr 29, 2026Qi Li, Yong Huang, Hui LiData Quality Outliers
Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of the Ministry of Industry and Information Technology, School of Civil Engineering, Harbin Institute of Technology, Harbin, 150090, China · Key Lab of Structures Dynamic Behavior and Control of the Ministry of Education, Harbin Institute of Technology, Harbin, 150090, China
Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models
Apr 29, 2026Zhirong Shen, Rui Huang, Jiacheng Liu +6Diffusion Transformers Diffusion Models
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 Models Perceptual Quality
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
Simple Self-Conditioning Adaptation for Masked Diffusion Models
Apr 28, 2026Michael Cardei, Huu Binh Ta, Ferdinando FiorettoMasked Diffusion Language Models Diffusion Models
University of Virginia
Benchmarking Layout-Guided Diffusion Models through Unified Semantic-Spatial Evaluation in Closed and Open Settings
Apr 28, 2026Luca Parolari, Nicla Faccioli, Lamberto BallanText-To-Image Diffusion Models
Department of Mathematics, University of Padova, Padova, Italy
The Thinking Pixel: Recursive Sparse Reasoning in Multimodal Diffusion Latents
Apr 28, 2026Yuwei Sun, Yuxuan Yao, Hui Li +1Multimodal Diffusion Models Diffusion Models
Shanghai Academy of AI for Science · Fudan University
Exploring Time Conditioning in Diffusion Generative Models from Disjoint Noisy Data Manifolds
Apr 28, 2026Liuzhuozheng Li, Zhiyuan Zhan, Shuhong Liu +5Text-Conditioned Diffusion Model Diffusion Models
SGIT AI Lab · UTokyo · RIKEN AIP +4
Generative diffusion models for spatiotemporal influenza forecasting
Apr 27, 2026Joseph Lemaitre, Justin LesslerEpidemiological Models Diffusion Models
Department of Epidemiology, Gillings School of Global Public Health, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA · Department of Epidemiology, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD 21205, USA · Carolina Population Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA
Learning Illumination Control in Diffusion Models
Apr 27, 2026Nishit Anand, Manan Suri, Christopher Metzler +2Illumination Variations Diffusion Models
University of Maryland College Park
Diffusion Model as a Generalist Segmentation Learner
Apr 27, 2026Haoxiao Wang, Antao Xiang, Haiyang Sun +8Open-Vocabulary Segmentation Diffusion Models
Zhejiang University · South China University of Technology · Nanjing University +1
Scaling Properties of Continuous Diffusion Spoken Language Models
Apr 27, 2026Jason Ramapuram, Eeshan Gunesh Dhekane, Amitis Shidani +6Speech Language Models Diffusion Language Models
Apple
Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion
Apr 27, 2026Zhongjie Duan, Hong Zhang, Yingda ChenDiffusion Models Plug-And-Play
ModelScope Team, Alibaba Group
GeoEdit: Local Frames for Fast, Training-Free On-Manifold Editing in Diffusion Models
Apr 27, 2026Yiming Zhang, Sitong Liu, Ke Li +3Diffusion-Based Image Editing Diffusion Models
University of California San Diego, La Jolla, CA, USA · University of Washington, Seattle, WA, USA · Xidian University, Xi’an, China
BiMol-Diff: A Unified Diffusion Framework for Molecular Generation and Captioning
Apr 27, 2026Aditya Hemant Shahane, Anuj Kumar Sirohi, Devansh Arora +3Molecular Generation Diffusion Models
Indian Institute of Technology Delhi · Indian Institute of Technology Ropar · Indian Institute of Science Bengaluru
FlowPlace: Flow Matching for Chip Placement
Apr 26, 2026Peng Xie, Ke Xue, Yunqi Shi +6Generative Flow Networks Layouts
1State Key Laboratory of Novel Software Technology, Nanjing University, China · School of Artificial Intelligence, Nanjing University, China · 3Huawei Noah’s Ark Lab, China
Discriminator-Guided Adaptive Diffusion for Source-Free Test-Time Adaptation under Image Corruptions
Apr 26, 2026Francesco Olivato, Cigdem Beyan, Vittorio MurinoDomain Adaptation Corrupted Inputs
Department of Computer Science, University of Verona, Verona, Italy · AI for Good (AIGO), Istituto Italiano di Tecnologia, Genova, Italy
On the Memorization of Consistency Distillation for Diffusion Models
Apr 26, 2026Bingqing Jiang, Difan ZouDataset Distillation Diffusion Models
School of Computing & Data Science, The University of Hong Kong. · School of Computing & Data Science and Institute of Data Science, The University of Hong Kong.
$Z^2$ -Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models
Apr 26, 2026Haosen Li, Wenshuo Chen, Shaofeng Liang +3Diffusion Sampling Diffusion Models
1The Hong Kong University of Science and Technology (Guangzhou) · 2Griffith University & Data61/CSIRO
Conditional Imputation for Within-Modality Missingness in Multi-Modal Federated Learning
Apr 25, 2026Wugeng Zheng, Ziwen Kan, Katie Wang +2Missing Modalities Imputation
University of Central Florida · Independent Researcher

May 6, 2026, cs.LGJ/K move · Enter open · S save

Conditional Diffusion Under Linear Constraints: Langevin Mixing and Information-Theoretic Guarantees

Ahmad Aghapour, Erhan Bayraktar, Asaf Cohen

Department of Mathematics University of Michigan Ann Arbor, MI 48109, USA

Bayesian Inverse Problems Diffusion Models Langevin Dynamics Tangent Space Inequality Constraints

Open paper AskPDF arXiv

We study zero-shot conditional sampling with pretrained diffusion models for linear inverse problems, including inpainting and super-resolution. In these problems, the observation determines only part of the unknown signal. The remaining degrees of freedom must be sampled according to the correct conditional data distribution. Existing projection-based samplers enforce measurement consistency by correcting the observed component during reverse diffusion. However, measurement consistency alone does not determine how probability mass should be distributed along the feasible set, and this can lead to biased conditional samples. We analyze this issue through a normal--tangent decomposition of the score function. For Gaussian noising, the observed-direction score is exactly determined by the measurement; only the tangent conditional score is unknown. We prove that the error from replacing this score by the unconditional tangent score is upper bounded by a dimension-free conditional mutual information between observed and unobserved components. This gives an information-theoretic decomposition into initialization and pathwise score-mismatch errors. Motivated by the theory, we propose a projected-Langevin initialization followed by guided reverse denoising, which outperforms a strong projection-based baseline in inpainting and super-resolution experiments.

Momentum

Related topics

Latest papers 934