Overview

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

CardsList

1,278 papers90 papers in the last four weeks, down 44% on the four weeks before. 0.7% of all new papers.

  1. Benchmarking Generative Models for Near-Surface Data Assimilation on Real Station Observations

    Sep 30, 2026Ruizhe Huang, Qidong Yang, Jonathan Giezendanner +1Flow MatchingData Assimilation

  2. From Modes to Memories: Characterizing the Scale-Space Dynamics of Diffusion Models

    Sep 30, 2026Cristina López Amado, Marco Fumero, Francesco LocatelloMemorization in Generative ModelsDiffusion Models

  3. D-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders

    Sep 30, 2026Xinyue Xu, Jiahao Zhang, Lijie Hu +2Transformer InterpretabilityDiffusion Transformer

  4. Why Do Conventional World Models Fail to Learn Cellular Automata?

    Sep 30, 2026Shaoyang Guo, Ziming LiuWorld Model LearningSpatiotemporal Reasoning

  5. ECHO-G: Embodied Co-speech Humanoid mOtion Generation

    Sep 30, 2026Yizhao Li, Pusen Gao, Ming Wang +3Text-to-Motion GenerationHuman Motion Generation

  6. CDMD: A Cross-Dataset Mixed-Type Diffusion Model for Tabular Data

    Sep 30, 2026Mohamed Amine Ketata, Maximilian Schambach, Stephan GünnemannMasked Diffusion ModelsTabular Diffusion Models

  7. Synchronous Multi-view Neural Diffusion

    Sep 30, 2026Yongquan Shi, Weijun Huang, Yueyang Pi +3Multi-View Diffusion ModelsMulti-View Learning

  8. MeshOctave: Vertex Split-and-Rewire Cascades for Native Mesh Generation

    Sep 30, 2026Junkai Lin, Tianhao Zhao, Hang Long +103D Mesh GenerationAdaptive Mesh Refinement

  9. Distilling Diffusion Score Discrepancy for Efficient Training Data Attribution

    Sep 30, 2026Shixuan Liu, Joan Serrà, Kin Wai Cheuk +6Gradient-Based AttributionKronecker-Factored Approximation

  10. GARDiff: Graph-Aligned Residual Diffusion for Probabilistic Multivariate Time-Series Forecasting

    Sep 29, 2026Rui Han, Min Yang, Xu Zhang +3Multivariate Time Series ForecastingGraph Structure Learning

  11. BeatDance: Generating Beat-Consistent 3D Dance with Hierarchical Spatial-Temporal Modeling

    Sep 29, 2026Xiaojian Shen, Dahu Shi, Jianrong Zhang +7Human Motion GenerationAudio-Visual Synchronization

  12. Improved Distributional Diffusion Models

    Sep 29, 2026Tommaso Martorella, Alexandre Galashov, Felix Krause +4Few-Step Diffusion SamplingDiffusion-Based Image Generation

  13. ZeroDiff: Zero-Shot Time Series Reconstruction via Informed-Prior Diffusion

    Sep 29, 2026Yingda Fan, Dan Lu, Xiaowei JiaTime Series ModelingDiffusion Models

  14. DiffReID: Discriminative Diffusion Model for Object Re-Identification

    Sep 29, 2026Yingquan Wang, Pingping Zhang, Dong Wang +1Representation LearningQuery Re-Identification

  15. FastVR: Efficient Streaming Video Restoration with One-Step Diffusion

    Sep 29, 2026Xiaoxu Chen, Qin Yang, Haoran Bai +2Diffusion TransformerVideo Restoration

  16. Sharp Convergence and Sampling Trade-offs for Riemannian Diffusion under Nonnegative Ricci Curvature

    Sep 29, 2026Yuhao Liu, Longbo HuangDiffusion Model SamplingDiffusion Models

  17. On the spectral properties of generative denoiser Jacobians

    Sep 28, 2026Alexandros Graikos, Nebojsa Jojic, Dimitris SamarasJacobian RegularizationDiffusion Models

  18. PreviewDiff: Multimodal Critic-Guided Search over Diffusion Latents

    Sep 28, 2026Vighnesh Subramaniam, Boris Katz, Brian Cheung +3Diffusion Model GuidanceT2I Generation

  19. Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion

    Sep 28, 2026Chong Wang, Zixuan Fu, Shiqi Huang +3Diffusion TransformerDiffusion Guidance

  20. FluxLite: Inference-Time Proposal Control for Discrete Diffusion Models

    Sep 28, 2026Yinuo Ren, Haoxuan Chen, Grant M. Rotskoff +2Diffusion SamplingDiffusion Models

  21. EnJoi: Ensemble Joint Score Filter for Generative Data Assimilation

    Sep 28, 2026Julien Moreau, Marc LelargeData AssimilationDiffusion Models

  22. Simplex Diffusion Models

    Sep 28, 2026Justin Deschenaux, Alexandre Galashov, Andrew Campbell +4Diffusion SamplingDiffusion Language Models

  23. First Learn, Then Memorize: The Spectral Bias of Diffusion Models

    Sep 28, 2026Raphaël Urfin, Tony Bonnaire, Giulio Biroli +1Neural Network GeneralizationMemorization in Generative Models

  24. Scaffold Then Internalize: Representation Injection for Diffusion Transformers

    Sep 28, 2026Han Fu, Jiacheng Chen, Baoquan Zhao +4Diffusion TransformerDiffusion Model Acceleration

  25. Learning to Re-Draft: A Variational Stackelberg Game for Discrete Diffusion

    Sep 28, 2026Dmitrii Moor, Federico Tomasi, Paul N. Bennett +2Bilevel OptimizationMolecular Generation

  26. Sol-H3: Recursive Self-Improvement for MiniMax-H3 Inference Acceleration on Sol-Engine across Cloud and Edge

    Sep 28, 2026Yitong Li, Jincheng Yu, Junsong Chen +6Video Diffusion ModelsGPU Kernel Optimization

  27. Retrieval-Augmented Diffusion Modeling for Stochastic Discount Factor Portfolios

    Sep 28, 2026Kelvin J. L. Koa, Xinyang Li, Ke-Wei HuangQuantitative FinancePortfolio Optimization

  28. Grab a Coffee: Future-Aware Guidance for Discrete Diffusion with Compiled Objectives

    Sep 28, 2026Hua, Xu, Dongxin Li +4Constrained Generative ModelingDiffusion Model Guidance

  29. Triangular Resampling for Long-Horizon Motion Generation

    Sep 28, 2026Kunhang Li, Yiyi Cai, Xiangyue Zhang +5Motion Diffusion ModelsHuman Motion Generation