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.

Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement
May 14, 2026Injin Kong, Hyoungjoon Lee, Yohan JoRepresentation Geometry Diffusion Language Models
Graduate School of Data Science, Seoul National University · Department of Biosystems & Biomaterials Science and Engineering, Seoul National University
D2-CDIG: Controlled Diffusion Remote Sensing Image Generation with Dual Priors of DEM and Cloud-Fog
May 14, 2026Zuopeng Zhao, Ying Liu, Kanyaphakphachsorn Pharksuwan +3Image Generation Remote Sensing
School of Computer Science and Technology/School of Artificial Intelligence, China University of Mining and Technology, Xuzhou 221116, China
Image Restoration via Diffusion Models with Dynamic Resolution
May 14, 2026Yang Zheng, Wen Li, Zhaoqiang LiuDiffusion Models for Image Restoration Diffusion-Based Inverse Problems
School of Computer Science and Engineering, University of Electronic Science and Technology of China.
Support Before Frequency in Discrete Diffusion
May 13, 2026Adrian Müller, Antoine Gonon, Zebang Shen +2Diffusion Language Models Diffusion Models
Department of Computer Science, ETH Zürich, Switzerland · Institute of Mathematics, EPFL, Switzerland · Institute of Statistical Science, Academia Sinica, Taiwan
Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers
May 13, 2026Evelyn Turri, Davide Bucciarelli, Sara Sarto +2Diffusion Transformer Massive Activations
University of Modena and Reggio Emilia, Italy · University of Pisa, Italy
Diffusion Models, Denoiser Architecture and Creativity
May 13, 2026Itamar Levine, Yair WeissGenerative Modeling Diffusion Models
The Hebrew University of Jerusalem
Learning to Optimize Radiotherapy Plans via Fluence Maps Diffusion Model Generation and LSTM-based Optimization
May 13, 2026Isabella Poles, Simon Arberet, Riqiang Gao +5Learning to Optimize Oncology
Politecnico di Milano, Milan, Italy · Digital Technology and Innovation, Siemens Healthineers, Princeton, NJ, USA · Digital Technology and Innovation, Siemens Healthineers, Erlangen, Germany
HetScene: Heterogeneity-Aware Diffusion for Dense Indoor Scene Generation
May 13, 2026Zini Chen, Junming Huang, Rong Zhang +43D Scene Generation 3D Scene Layout Generation
OP4KSR: One-Step Patch-Free 4K Super-Resolution with Periodic Artifact Suppression
May 13, 2026Chengyan Deng, Pengbin Yu, Zhentao Chen +6Diffusion Transformer Diffusion Model Inference Acceleration
School of Automation Engineering, University of Electronic Science and Technology of China · OPPO AI Center, OPPO Inc. · School of Intelligence Science and Technology, Nanjing University
On the Limits of Latent Reuse in Diffusion Models
May 13, 2026Yifeng Yu, Lu YuLatent Diffusion Models Domain Adaptation
Department of Mathematical Sciences, Tsinghua University · Department of Data Science, City University of Hong Kong
Seconds-Aligned PCA-DAC Latent Diffusion for Symbolic-to-Audio Drum Rendering
May 13, 2026Konstantinos Soiledis, Maximos Kaliakatsos Papakostas, Dimos Makris +1Latent Diffusion Models Symbolic Music Generation
1Dept. of Music Technology and Acoustics, Hellenic Mediterranean University, Rethymno & Athens, Greece · 2Athena RC, Athens, Greece
The Diffusion Encoder
May 13, 2026Akhil Premkumar, Sarah LucioniVariational Autoencoders Diffusion Models
Independent Researcher
Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation
May 13, 2026Junhyuk Jeon, Seokhyeon Hong, Junyong NohText-to-Motion Generation Diffusion Models
Visual Media Lab, KAIST, Daejeon, Republic of Korea
Discrete Diffusion for Complex and Congested Multi-Agent Path Finding with Sparse Social Attention
May 13, 2026Yuanzhe Wang, Tian Zhi, Zihang Wei +8Multi-Agent System Optimization Diffusion-Based Planning
State Key Lab of Processors, Institute of Computing Technology, CAS · School of Advanced Interdisciplinary Sciences, CAS · University of Chinese Academy of Sciences +1
Do Heavy Tails Help Diffusion? On the Subtle Trade-off Between Initialization and Training
May 13, 2026Hamza Cherkaoui, Hélène Halconruy, Antonio OcelloDiffusion Model Sampling Heavy-Tailed Noise
SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris, Palaiseau, France · Modal’X, Université Paris Nanterre, Nanterre, France · CREST, ENSAE Paris, Institut Polytechnique de Paris, Palaiseau, France
DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number Defense
May 13, 2026Ziyang You, Liling Zheng, Xiaoke Yang +1Backdoor Attacks Diffusion Models
School of Electronics, Electrical Engineering and Physics, Fujian University of Technology, Fuzhou 350118, China · School of Humanities, Fujian University of Technology, Fuzhou 350118, China · Institute of Applied Physics and Materials Engineering, University of Macau, Macau 999078, China
EgoForce: Robust Online Egocentric Motion Reconstruction via Diffusion Forcing
May 13, 2026Inwoo Hwang, Donggeun Lim, Hojun Jang +1Markerless Motion Capture Egocentric Video Understanding
Seoul National University
Discrete Stochastic Localization for Non-autoregressive Generation
May 13, 2026Yunshu Wu, Jiayi Cheng, Longxuan Yu +4Non-Autoregressive Text Generation Masked Diffusion Models
University of California Riverside · New York University
The critical slowing down in diffusion models
May 12, 2026Luca Maria Del Bono, Giulio Biroli, Patrick Charbonneau +1Diffusion Sampling Critical Slowing Down
Dipartimento di Fisica, Sapienza Università di Roma, Piazzale Aldo Moro 5, Rome 00185, Italy · CNR-Nanotec, Rome unit, Piazzale Aldo Moro 5, Rome 00185, Italy · Laboratoire de Physique Statistique, École normale supérieure, PSL Research University, 24 rue Lhomond, 75005 Paris, France +3
UniFixer: A Universal Reference-Guided Fixer for Diffusion-Based View Synthesis
May 12, 2026Sihan Chen, Xiang Zhang, Yang Zhang +2Diffusion Models for Image Restoration Novel View Synthesis
ETH Zürich, Switzerland · DisneyResearch|Studios, Switzerland
Machine Learning for neutron source distributions
May 12, 2026Jose Ignacio Robledo, Norberto Schmidt, Klaus Lieutenant +3Generative Modeling Diffusion Models
Jülich Centre for Neutron Science (JCNS-2), Forschungszentrum Jülich, Jülich, Germany · Jülich Supercomputing Centre (JSC), Forschungszentrum Jülich, Jülich, Germany
Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning
May 12, 2026Hyeonjin Kim, Hangyeol Jung, Heechan Yun +2Disentangled Representation Learning Sparse Autoencoders
Yonsei University · KAIST
L2P: Unlocking Latent Potential for Pixel Generation
May 12, 2026Zhennan Chen, Junwei Zhu, Xu Chen +7Latent Diffusion Models Pixel-Space Diffusion Models
Nanjing University · Tencent Youtu Lab · Hainan-biuh +1
RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decomposition
May 12, 2026Binhao Wang, Shihao Zhao, Bo Cheng +6Diffusion Models
1Wenzhou University · AI Research
Is Monotonic Sampling Necessary in Diffusion Models?
May 12, 2026Muhammad Haris KhanDiffusion Sampling Diffusion Timestep Scheduling
Department of Computer Science, University of Copenhagen, Denmark
Overcoming the Intrinsic Performance Limitations of MEMS IMU via Diffusion-Based Generative Learning
May 12, 2026Jiarui Lv, Feng Zhu, Xiaohong ZhangSynthetic Data Generation for Robotics Inertial Navigation
School of Geodesy and Geomatics, Wuhan University, Wuhan, Hubei 430079, China · School of Geodesy and Geomatics, and Hubei Luojia Laboratory, Wuhan University, Wuhan, Hubei 430079, China · School of Geodesy and Geomatics, Hubei Luojia Laboratory, and Chinese Antarctic Center of Surveying and Mapping, Wuhan University, Wuhan, Hubei 430079, China
Generative climate downscaling enables high-resolution compound risk assessment by preserving multivariate dependencies
May 12, 2026Takuro Kutsuna, Noriko N. Ishizaki, Norihiro Oyama +1Climate Science Climate Modeling
Toyota Central R&D Labs., Inc. · National Institute for Environmental Studies
FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion Models
May 12, 2026Abtin Mahyar, Masoumeh Shafieinejad, Yuhan Liu +1Membership Inference Attacks Tabular Diffusion Models
University of Waterloo · Vector Institute
ZeroIDIR: Zero-Reference Illumination Degradation Image Restoration with Perturbed Consistency Diffusion Models
May 12, 2026Hai Jiang, Zhen Liu, Yinjie Lei +3Low-Light Image Enhancement Image Restoration
School of Aeronautics and Astronautics, Sichuan University · University of Electronic Science and Technology of China · College of Electronics and Information Engineering, Sichuan University
Couple to Control: Joint Initial Noise Design in Diffusion Models
May 11, 2026Jing Jia, Liyue Shen, Guanyang WangDiffusion Sampling Image Generation
Department of Computer Science Rutgers University Piscataway, NJ 08854 · Department of EECS University of Michigan Ann Arbor, MI 48109 · Department of Statistics Rutgers University Piscataway, NJ 08854

May 14, 2026J/K move · Enter open · S save

Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement

Injin Kong, Hyoungjoon Lee, Yohan Jo

Graduate School of Data Science, Seoul National University · Department of Biosystems & Biomaterials Science and Engineering, Seoul National University

Representation Geometry Diffusion Language Models Continuous Diffusion Language Models Conditional Diffusion Models Diffusion Models

Open paper AskPDF arXiv

Continuous diffusion language models require choosing a representation space in which denoising operates, yet it remains unclear which representations are most compatible with diffusion. We study a basic design question: where inside a pretrained language model should continuous diffusion operate? We formulate this as a hidden-state interface-selection problem and hypothesize that diffusion-friendly interfaces can be identified from representation geometry. We operationalize this hypothesis using three training-free geometric proxies: local compactness, global stiffness, and effective rank. Across two 8B-scale backbones, the resulting geometry score predicts fixed-budget diffusion bridgeability beyond the dominant effect of layer depth. We then instantiate DiHAL, a Locate-and-Replace framework that replaces the transformer prefix below a selected interface with conditional diffusion while retaining the pretrained suffix and LM head. Under full training, geometry-selected interfaces remain close to validation-loss oracles and outperform worst-layer controls, while the diffusion bridge outperforms a parameter-matched deterministic replacement under matched diagnostic conditions. These results suggest that the representation space in which diffusion operates should itself be treated as a first-class design variable for continuous diffusion in language models.