Diffusion Model Acceleration

Ask about this topic

Overview

Diffusion model acceleration studies how to make iterative denoising models faster and cheaper to train and run across images, video, language, and scientific applications. Common approaches reduce the number of denoising steps through distillation, consistency learning, or adaptive solvers, and reduce work per step through caching, token or attention sparsity, quantization, and efficient architectures. Research also targets training throughput and deployment, using optimized kernels, parallelism, and compact models on settings such as text-to-image benchmarks, long-video generation, and medical imaging. The central challenge is balancing real wall-clock speed and memory savings against fidelity, diversity, and temporal consistency, since effective shortcuts can depend on the model, task, and denoising stage.

Latest papers

CardsList

141 papers21 papers in the last four weeks, up 133% on the four weeks before. 0.1% of all new papers.

  1. A Few-Step Generative Model on Cumulative Flow Maps

    May 5, 2026Zhiqi Li, Duowen Chen, Yuchen Sun +1One-Step Generative ModelingFlow-Based Generative Modeling

    Georgia Institute of Technology, Atlanta, United States of America

  2. AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers

    May 5, 2026Ruibin Min, Yexin Liu, Aimin Pan +5Diffusion Model AlignmentDiffusion Transformer

    Sun Yat-sen University · The Hong Kong University of Science and Technology · VNET Group +2

  3. TOC-SR: Task-Optimal Compact diffusion for Image Super Resolution

    May 4, 2026Sowmya Vajrala, Akshay Bankar, Manjunath Arveti +5Diffusion DistillationFew-Step Diffusion Sampling

    Samsung Research Institute Bangalore, India

  4. Skipping the Zeros in Diffusion Models for Sparse Data Generation

    May 3, 2026Phil Sidney Ostheimer, Mayank Nagda, Andriy Balinskyy +6Synthetic Data GenerationDiffusion Model Acceleration

    1RPTU University Kaiserslautern-Landau · 2Heidelberg Univer · University of California, Irvine.

  5. Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control

    May 2, 2026Jinhao Zhang, Zhexuan Zhou, Huizhe Li +5Visuomotor Policy LearningDiffusion Policy

    Harbin Institute of Technology, Shenzhen · Shanghai Jiao Tong University

  6. SwiftPie: Lightning-fast Subject-driven Image Personalization via One step Diffusion

    May 2, 2026Huy Duong, Trong-Tung Nguyen, Cuong Pham +3Subject-Driven Image GenerationIdentity-Preserving Image Generation

    Qualcomm AI Research

  7. Consistent Diffusion Language Models

    Apr 30, 2026Hasan Amin, Yuan Gao, Yaser Souri +4Few-Step Diffusion SamplingDiffusion Model Acceleration

    Department of Computer Science, Purdue University · Microsoft

  8. Accelerating trajectory optimization with Sobolev-trained diffusion policies

    Apr 21, 2026Théotime Le Hellard, Franki Nguimatsia Tiofack, Quentin Le Lidec +1Trajectory OptimizationTrajectory Generation

    Inria - Département d’Informatique de l’École normale supérieure, PSL Research University, France · Courant Institute, New York University, USA

  9. Optimally Bridging Semantics and Data: Generative Semantic Communication via Schrödinger Bridge

    Apr 20, 2026Dahua Gao, Ruichao Liu, Minxi Yang +3Semantic CommunicationFew-Step Diffusion Sampling

    School of Artificial Intelligence, Xidian University, Xi’an, Shaanxi 710071 China · Pazhou Lab, Huangpu, Guangdong 510555 China · Peng Cheng Laboratory, Shenzhen, Guangdong 518055 China +1

  10. Structure-Adaptive Sparse Diffusion in Voxel Space for 3D Medical Image Enhancement

    Apr 20, 2026Hongxu Jiang, Fei Li, Boxiao Yu +43D Medical ImagingMedical Image Super-Resolution

    Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL, USA · Department of Medicine, University of Florida, Gainesville, FL, USA · Department of Biomedical Engineering, University of Florida, Gainesville, FL +2

  11. MaMe & MaRe: Matrix-Based Token Merging and Restoration for Efficient Visual Perception and Synthesis

    Apr 15, 2026Simin Huo, Ning LiVisual Token MergingVisual Token Compression

    Shanghai Jiao Tong University, , Shanghai, 200240, Shanghai, China

  12. Nucleus-Image: Sparse MoE for Image Generation

    Apr 14, 2026Chandan Akiti, Ajay Modukuri, Murali Nandan Nagarapu +2T2I Diffusion ModelsDiffusion Models

  13. Training-free, Perceptually Consistent Low-Resolution Previews with High-Resolution Image for Efficient Workflows of Diffusion Models

    Apr 10, 2026Wongi Jeong, Hoigi Seo, Se Young ChunImage GenerationDiffusion Model Acceleration

    Dept. of Electrical and Computer Engineering, Seoul National University, Republic of Korea · INMC & IPAI, Seoul National University, Republic of Korea

  14. Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

    Apr 10, 2026Zile Wang, Zexiang Liu, Jiaxing Li +20Real-Time Interactive Video GenerationLong-Horizon Video Generation

    Skywork AI

  15. Bias-Constrained Diffusion Schedules for PDE Emulations: Reconstruction Error Minimization and Efficient Unrolled Training

    Apr 9, 2026Constantin Le Cleï, Nils Thuerey, Xiaoxiang ZhuDiffusion ModelsAutoregressive Diffusion

    Technical University of Munich, Munich, Germany.

  16. FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling

    Apr 8, 2026Yitong Li, Junsong Chen, Shuchen Xue +8Diffusion Model AlignmentRL for Diffusion Models

    NVIDIA · HKU · MIT

  17. Data Warmup: Complexity-Aware Curricula for Efficient Diffusion Training

    Apr 8, 2026Jinhong Lin, Pan Wang, Zitong Zhan +2Diffusion-Based Image GenerationCurriculum Learning

    University of Wisconsin–Madison · University of Pittsburgh · University at Buffalo, SUNY

  18. RdmR_\text{dm}: Re-conceptualizing Distribution Matching as a Reward for Diffusion Distillation

    Mar 30, 2026Linqian Fan, Peiqin Sun, Tiancheng Wen +2Diffusion Model DistillationDistribution Matching Distillation

    KlingAI Research · Tsinghua University

  19. EFlow: Fast Few-Step Video Generator Training from Scratch via Efficient Solution Flow

    Mar 28, 2026Dogyun Park, Yanyu Li, Sergey Tulyakov +1Video Diffusion ModelsDiffusion Model Acceleration

    Snap Inc. · Korea University, Seoul, Republic of Korea

  20. MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model

    Mar 27, 2026Quan Dao, Dimitris MetaxasDiffusion TransformerDiffusion-Based Image Generation

    Rutgers University

  21. DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving

    Mar 25, 2026Pengxuan Yang, Yupeng Zheng, Deheng Qian +11RL for Autonomous DrivingLatent World Models

    Institute of Automation, CAS · Chongqing Chang’an Technology Co., Ltd · School of Advanced Interdisciplinary Sciences, UCAS +1

  22. Foveated Diffusion: Efficient Spatially Adaptive Image and Video Generation

    Mar 24, 2026Brian Chao, Lior Yariv, Howard Xiao +1Adaptive TokenizationDiffusion Model Acceleration

    Stanford University, USA

  23. DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolution

    Mar 23, 2026Zhengyao Lv, Menghan Xia, Xintao Wang +1Video Super-ResolutionDiffusion Model Distillation

    The University of Hong Kong · Huazhong University of Science and Technology · Kling Team, Kuaishou Technology

  24. Timestep-Aware Block Masking for Efficient Diffusion Model Inference

    Mar 20, 2026Haodong He, Yuan Gao, Weizhong Zhang +1Diffusion Model AccelerationDiffusion Model Inference Acceleration

    School of Computer Science, Wuhan University · School of Artificial Intelligence, Wuhan University · School of Data Science, Fudan University

  25. PDE-SSM: A Spectral State Space Approach to Spatial Mixing in Diffusion Transformers

    Mar 14, 2026Eshed Gal, Moshe Eliasof, Eldad HaberDiffusion TransformerVisual SSMs

    University of British Columbia, Vancouver, BC Canada · University of Cambridge, Cambridge, United Kingdom

  26. BiGain: Unified Token Compression for Joint Generation and Classification

    Mar 12, 2026Jiacheng Liu, Shengkun Tang, Jiacheng Cui +2Token CompressionDiffusion Model Compression

    VILA Lab, MBZUAI · North Carolina State University

  27. Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation

    Mar 10, 2026Junyi An, Chao Qu, Yun-Fei Shi +33D Molecular GenerationMolecular Generation

    Shanghai Academy of Artificial Intelligence for Science, SAIS · Artificial Intelligence Innovation and Incubation (AI3) Institute, Fudan University

  28. Streaming Autoregressive Video Generation via Diagonal Distillation

    Mar 10, 2026Jinxiu Liu, Xuanming Liu, Kangfu Mei +3Streaming Video GenerationAutoregressive Video Generation

    South China University of Technology · Westlake University · Johns Hopkins University +2

  29. Reviving ConvNeXt for Efficient Convolutional Diffusion Models

    Mar 10, 2026Taesung Kwon, Lorenzo Bianchi, Lennart Wittke +5Diffusion ModelsDiffusion Model Acceleration

    KAIST · ETH Zürich · ISTI-CNR +2

  30. Scale Space Diffusion

    Mar 9, 2026Soumik Mukhopadhyay, Prateksha Udhayanan, Abhinav ShrivastavaPixel-Space Diffusion ModelsDiffusion Model Acceleration

    University of Maryland, College Park