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.

HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer
May 11, 2026Qi Cai, Jingwen Chen, Chengmin Gao +22Diffusion Transformer Text-Guided Image Editing
Elucidating Representation Degradation Problem in Diffusion Model Training
May 11, 2026Zhipeng Yao, Dazhou Li, Zitong Zhang +6Deep Learning Optimization Diffusion Model Acceleration
University of Louisville · Shenyang University of Chemical Technology · Florida International University +2
Heteroscedastic Diffusion for Multi-Agent Trajectory Modeling
May 11, 2026Guillem Capellera, Antonio Rubio, Luis Ferraz +1Multi-Agent Trajectory Prediction Trajectory Prediction
Institut de Rob`otica i Inform`atica Industrial, CSIC-UPC, Barcelona, 08028, Spain · Kognia Sports Intelligence, 08960, Sant Just Desvern, Spain
diffGHOST: Diffusion based Generative Hedged Oblivious Synthetic Trajectories
May 11, 2026Florent Guépin, Cheick Tidiani Cisse, Denis Renaud +2Trajectory Generation Synthetic Data Generation
Orange Research, Belfort, France · Orange Business, Belfort, France
GenMed: A Pairwise Generative Reformulation of Medical Diagnostic Tasks
May 11, 2026Hantao Zhang, Weidong Guo, Yuhe Liu +5Cross-Modality Medical Image Segmentation Diffusion Model Guidance
CVLab, École Polytechnique Fédérale de Lausanne (EPFL), Switzerland · Fudan University, Shanghai, China · Beihang University, Beijing, China +3
Composing diffusion priors with explicit physical context via generative Gibbs sampling
May 11, 2026Weizhou Wang, Jonathan Weare, Aaron R. DinnerDiffusion Posterior Sampling Diffusion Models
Department of Chemistry University of Chicago Chicago, IL 60637 · Courant Institute of Mathematical Sciences New York University New York, NY 10012
Product-of-Gaussian-Mixture Diffusion Models for Joint Nonlinear MRI Reconstruction
May 11, 2026Laurenz Nagler, Martin Zach, Thomas PockAccelerated MRI Reconstruction Magnetic Resonance Imaging
Graz University of Technology, Institute of Visual Computing, 8010 Graz, Austria. · Ecole Polytechnique Fédérale de Lausanne, Biomedical Imaging Group and Center for Biomedical Imaging, 1015 Lausanne, Switzerland.
Infinite Mask Diffusion for Few-Step Distillation
May 11, 2026Jaehoon Yoo, Wonjung Kim, Chanhyuk Lee +1Masked Diffusion Models Diffusion Model Distillation
Korea Advanced Institute of Science and Technology (KAIST)
Filtering Memorization from Parameter-Space in Diffusion Models
May 11, 2026Yu Zhe, Yang Jiayan, Wei Junhao +2Low-Rank Adaptation Memorization in Generative Models
RIKEN AIP · Institute of Science Tokyo · University of California, Berkeley +1
A Stability Benchmark of Generative Regularizers for Inverse Problems
May 11, 2026Alexander Denker, Johannes Hertrich, Sebastian NeumayerGenerative Modeling Diffusion-Based Inverse Problems
Helmholtz Imaging, Deutsches Elektronen-Synchrotron DESY, Germany · ENS Paris & Inria, France · Chemnitz University of Technology, Germany
TrajDLM: Topology-Aware Block Diffusion Language Model for Trajectory Generation
May 11, 2026Wilson Wongso, Lihuan Li, Arian Prabowo +4Trajectory Generation Synthetic Data Generation
University of New South Wales · Hong Kong University of Science and Technology (Guangzhou)
The two clocks and the innovation window: When and how generative models learn rules
May 11, 2026Binxu Wang, Emma Lucia Byrnes Finn, Bingbin LiuMemorization in Generative Models Generative Modeling
Kempner Institute at Harvard University
TD3B: Transition-Directed Discrete Diffusion for Allosteric Binder Generation
May 10, 2026Hanqun Cao, Aastha Pal, Sophia Tang +4Molecular Generation Protein Design
Department of Computer Science and Engineering, The Chinese University of Hong Kong · Department of Bioengineering, University of Pennsylvania · Department of Computer and Information Science, University of Pennsylvania +1
Primal-Dual Guided Decoding for Constrained Discrete Diffusion
May 10, 2026Federico Tomasi, Dmitrii Moor, Alice Wang +1Primal-Dual Optimization Constrained Generative Modeling
Spotify
Backbone-Equated Diffusion OOD via Sparse Internal Snapshots
May 10, 2026Yadang Alexis Rouzoumka, Jean Pinsolle, Eugénie Terreaux +3Diffusion-Based OOD Detection OOD Detection
DEMR, ONERA & SONDRA · Université Paris-Saclay · SONDRA, CentraleSupélec +1
PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models
May 10, 2026Yongsen Cheng, Kai Liu, Kaiwen Tao +5Diffusion Model Quantization Post-Training Quantization
Shanghai Jiao Tong University · Huawei Noah’s Ark Lab
AtteConDA: Attention-Based Conflict Suppression in Multi-Condition Diffusion Models and Synthetic Data Augmentation
May 10, 2026Shogo NoguchiSynthetic Data Augmentation Conditional Image Generation
Gunma University
PGID: Progressive Guided Inversion and Denoising for Robust Watermark Detection
May 10, 2026Minh Quoc Duong, Chun Tong Lei, Chun Pong LauDiffusion Model Inversion Diffusion Model Watermarking
City University of Hong Kong
Attention Sinks in Diffusion Transformers: A Causal Analysis
May 10, 2026Fangzheng Wu, Brian SummaTransformer Interpretability Diffusion Transformer
Department of Computer Science, Tulane University, New Orleans, LA, USA.
Discrete Langevin-Inspired Posterior Sampling
May 10, 2026Chaitanya Amballa, Sattwik Basu, Jorge Vančo Sampedro +1Diffusion Models for Image Restoration Bayesian Inverse Problems
University of Illinois Urbana-Champaign
DiffATS: Diffusion in Aligned Tensor Space
May 10, 2026Jinhua Lyu, Tianmin Yu, Brian Kim +3Orthogonal Procrustes Alignment Tensor Decomposition
Northwestern University
Dependency-Aware Discrete Diffusion for Scene Graph Generation
May 9, 2026Rajalaxmi Rajagopalan, Romit Roy ChoudhuryScene Graph Generation Diffusion Models
University of Illinois, Urbana-Champaign
SynerDiff: Synergetic Continuous Batching for Fast and Parallel Diffusion Model Inference
May 9, 2026Ziqi Zhou, Peng Yang, Yuxin Liang +2Diffusion Model Serving Diffusion Model Inference Acceleration
School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China · The State Grid Hubei Electric Power Research Institute, Wuhan, China · Jincheng Yunxiang Big Data Technology Operation Co., Ltd., Shanxi, China
TARO: Temporal Adversarial Rectification Optimization Using Diffusion Models as Purifiers
May 8, 2026Daniel Wesego, Pedram RooshenasDiffusion Model Guidance Adversarial Robustness
Department of Computer Science · University of Illinois Chicago · Chicago, IL 60607
Geometry-Aware Discretization Error of Diffusion Models
May 8, 2026Samuel Hurault, Thomas Moreau, Gabriel PeyréDiffusion Sampling Few-Step Diffusion Sampling
Univ. Gustave Eiffel, CNRS, LIGM · Univ. Paris-Saclay, Inria, CEA · CNRS, ENS, PSL Université
Normalizing Trajectory Models
May 8, 2026Jiatao Gu, Tianrong Chen, Ying Shen +3Normalizing Flows Diffusion Model Distillation
Apple · UIUC
DVD: Discrete Voxel Diffusion for 3D Generation and Editing
May 8, 2026Zhengrui Xiang, Jiaqi Wu, Fupeng Sun +23D Shape Editing 3D Shape Generation
Imperial College London · Math Magic, Hitem3D · Math Magic
What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion
May 8, 2026Zhengrong Yue, Taihang Hu, Mengting Chen +8Latent Diffusion Models Autoencoders
Shanghai Jiao Tong University · Alibaba Group · Beihang University +4
Inference-Time Attribute Distribution Alignment for Unconditional Diffusion
May 8, 2026Hao Luan, See-Kiong Ng, Chun Kai LingControllable Image Generation Inference-Time Guidance
School of Computing, National University of Singapore · Institute of Data Science, National University of Singapore
Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework
May 8, 2026Linxiao Shi, Siming Zheng, Zerong Wang +5Neural Rendering Image Super-Resolution
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · vivo BlueImage Lab, vivo Mobile Communication Co., Ltd. · Shenzhen University of Advanced Technology

May 11, 2026J/K move · Enter open · S save

HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer

Qi Cai, Jingwen Chen, Chengmin Gao, Zijian Gong+21

Diffusion Transformer Text-Guided Image Editing Unified Multimodal Models Pixel-Space Diffusion Models Multimodal Foundation Models T2I Diffusion Models+1

Open paper AskPDF arXiv

The evolution of visual generative models has long been constrained by fragmented architectures relying on disjoint text encoders and external VAEs. In this report, we present HiDream-O1-Image, a natively unified generative foundation model via pixel-space Diffusion Transformer, that pioneers a paradigm shift from modular architectures to an end-to-end in-context visual generation engine. By mapping raw image pixels, text tokens, and task-specific conditions into a single shared token space, HiDream-O1-Image achieves a structural unification of multimodal inputs within an Unified Transformer (UiT) architecture. This native encoding paradigm eliminates the need for separate VAEs or disjoint pre-trained text encoders, allowing the model to treat diverse generation and editing tasks as a consistent in-context reasoning process. Extensive experiments show that HiDream-O1-Image excels across various generation tasks, including text-to-image generation, instruction-based editing, and subject-driven personalization. Notably, with only 8B parameters, HiDream-O1-Image (8B) achieves performance parity with or even surpasses established state-of-the-art models with significantly larger parameters (e.g., 27B Qwen-Image). Crucially, to validate the immense scalability of this paradigm, we successfully scale the architecture up to over 200B parameters. Experimental results demonstrate that this massive-scale version HiDream-O1-Image-Pro (200B+) unlocks unprecedented generative capabilities and superior performance, establishing new state-of-the-art benchmarks. Ultimately, HiDream-O1-Image highlights the immense potential of natively unified architectures and charts a highly scalable path toward next-generation multimodal AI.