Diffusion Model Inference Acceleration

Ask about this topic

Overview

Diffusion models repeatedly denoise a sample, so inference acceleration studies how to reduce the cost of those steps for image, video, language, and action generation. Methods reduce the number of evaluations with faster solvers, timestep schedules, and few-step distillation, or reduce work within each step using caching, sparse attention, token pruning, compression, and lower-precision computation. Systems work also targets memory movement, GPU parallelism, and serving, while adaptive methods allocate computation according to uncertainty, content, or task difficulty. The central challenge is preserving fidelity, diversity, and task accuracy as skipped or approximated computations can accumulate errors; gains therefore depend on the model, workload, hardware, and end-to-end evaluation.

Latest papers

CardsList

509 papers73 papers in the last four weeks, up 66% on the four weeks before. 0.4% of all new papers.

  1. Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment

    Apr 27, 2026Kaijun Zhou, Qiwei Chen, Da Peng +3AI Accelerator InferenceEdge Inference

    School of Computer Science, Shanghai Jiao Tong University

  2. Latent Inter-Frame Pruning: A Training-Free Method Bridging Traditional Video Compression and Modern Diffusion Transformers for Efficient Generation

    Apr 26, 2026Dennis Menn, Chih-Hsien ChouVideo Diffusion ModelsToken Pruning

    The University of Texas at Austin · Futurewei Technologies, Inc.

  3. Z2Z^2-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models

    Apr 26, 2026Haosen Li, Wenshuo Chen, Shaofeng Liang +3Diffusion Model AlignmentDiffusion Sampling

    1The Hong Kong University of Science and Technology (Guangzhou) · 2Griffith University & Data61/CSIRO

  4. VS-DDPM: Efficient Low-Cost Diffusion Model for Medical Modality Translation

    Apr 24, 2026Nikoo Moradi, Gijs Luijten, Behrus Hinrichs-Puladi +4Image-to-Image Translation3D Medical Imaging

    Institute for Artificial Intelligence in Medicine (IKIM), Essen University Hospital (AöR), University of Duisburg-Essen, Essen, Germany · Institute of Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16, Graz, 8010, Austria · Center for Virtual and Extended Reality in Medicine (ZvRM), University Hospital Essen (AöR), Essen, Germany +7

  5. Accelerating Frequency Domain Diffusion Models with Error-Feedback Event-Driven Caching

    Apr 24, 2026Dong Liu, Haisheng Wang, Yanxuan YuTime Series GenerationDiffusion Model Caching

    University of California, Los Angeles · Yale University · East China Normal University +1

  6. MISTY: High-Throughput Motion Planning via Mixer-based Single-step Drifting

    Apr 23, 2026Yining Xing, Zehong Ke, Yiqian Tu +3Trajectory GenerationDiffusion-Based Planning

    School of Vehicle and Mobility, Tsinghua University, Beijing, China · State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China

  7. Sparse Forcing: Native Trainable Sparse Attention for Real-time Autoregressive Diffusion Video Generation

    Apr 23, 2026Boxun Xu, Yuming Du, Zichang Liu +7Autoregressive DiffusionSelf-Attention

    Meta Superintelligence Labs · University of California, Santa Barbara · Work done at Meta

  8. DynamicRad: Content-Adaptive Sparse Attention for Long Video Diffusion

    Apr 22, 2026Yongji Long, Shijun Liang, Jintao Li +1Video Diffusion ModelsLong-Horizon Video Generation

    University of Electronic Science and Technology of China · Shenzhen Institute for Advanced Study, UESTC · Computational Mathematics, Science, & Engineering at Michigan State University (MSU)

  9. X-Cache: Cross-Chunk Block Caching for Few-Step Autoregressive World Models Inference

    Apr 22, 2026Yixiao Zeng, Jianlei Zheng, Chaoda Zheng +10Video Diffusion ModelsDiffusion Model Caching

    AI Infra Team, XPeng Inc.

  10. FASTER: Value-Guided Sampling for Fast RL

    Apr 21, 2026Perry Dong, Alexander Swerdlow, Dorsa Sadigh +1Diffusion SamplingDiffusion Policy

    Stanford University

  11. Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation

    Apr 21, 2026Johannes Schusterbauer, Ming Gui, Yusong Li +3Diffusion Model SamplingDiffusion Sampling

  12. NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization

    Apr 20, 2026Enshu Liu, Xuefei Ning, Yu Wang +1Few-Step Diffusion SamplingDiffusion Language Model Decoding

    Department of EE, Tsinghua University · Microsoft Research

  13. One-Step Diffusion with Inverse Residual Fields for Unsupervised Industrial Anomaly Detection

    Apr 20, 2026Boan Zhang, Wen Li, Guanhua Yu +3Industrial Anomaly DetectionUnsupervised Anomaly Detection

    Department of Computer Science and Technology Xidian University Shaanxi, China 710126 · Department of Electronic Engineering Xidian University Shaanxi, China 710126

  14. AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation

    Apr 20, 2026Haoyue Tan, Shengnan Wang, Yulin Qiao +5Video Diffusion ModelsDiffusion Transformer

    University of Science and Technology of China · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center · 3Independent Researcher +2

  15. Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing

    Apr 20, 2026Kijung Jeon, Michael Muehlebach, Molei TaoConstrained Generative ModelingLangevin Dynamics

    Georgia Institute of Technology · Max Planck Institute for Int. Sys.

  16. Speculative Decoding for Autoregressive Video Generation

    Apr 19, 2026Yuezhou Hu, Jintao ZhangVideo Diffusion ModelsAutoregressive Diffusion

    University of California, Berkeley

  17. VADF: Vision-Adaptive Diffusion Policy Framework for Efficient Robotic Manipulation

    Apr 17, 2026Xinglei Yu, Zhenyang Liu, Shufeng Nan +2Adaptive InferenceDiffusion Policy

    Fudan University · Shanghai Innovation Institute

  18. Efficient Video Diffusion Models: Advancements and Challenges

    Apr 17, 2026Shitong Shao, Lichen Bai, Pengfei Wan +2Model CompressionVideo Diffusion Models

    The Hong Kong University of Science and Technology (Guangzhou), China · Kling Team, Kuaishou Technology, China · The Hong Kong University of Science and Technology, Hong Kong

  19. Thermodynamic Diffusion Inference with Minimal Digital Conditioning

    Apr 15, 2026Aditi DeAnalog ComputingDiffusion Models

  20. CoD-Lite: Real-Time Diffusion-Based Generative Image Compression

    Apr 14, 2026Zhaoyang Jia, Naifu Xue, Zihan Zheng +7Generative Image CompressionLearned Image Compression

    University of Science and Technology of China · Communication University of China · Microsoft Research Asia

  21. FreqFormer: Hierarchical Frequency-Domain Attention with Adaptive Spectral Routing for Long-Sequence Video Diffusion Transformers

    Apr 14, 2026Haopeng JinDiffusion Model Inference AccelerationDiffusion Transformer

    Beijing University of Posts and Telecommunications

  22. Ride the Wave: Precision-Allocated Sparse Attention for Smooth Video Generation

    Apr 14, 2026Wentai Zhang, Ronghui Xi, Shiyao Peng +4Sparse AttentionDiffusion Model Inference Acceleration

    Beijing University of Posts and Telecommunications, Beijing, China · Nanyang Technological University, Singapore, Singapore

  23. LoSA: Locality Aware Sparse Attention for Block-Wise Diffusion Language Models

    Apr 13, 2026Haocheng Xi, Harman Singh, Yuezhou Hu +9Diffusion Language Model InferenceDiffusion Model Inference Acceleration

    University of California, Berkeley · FuriosaAI · ICSI +2

  24. Energy-oriented Diffusion Bridge for Image Restoration with Foundational Diffusion Models

    Apr 13, 2026Jinhui Hou, Zhiyu Zhu, Junhui HouDiffusion Models for Image RestorationDiffusion Models

    Department of Computer Science, City University of Hong Kong · Department of Computer Science, City University of Hong Kong (Dongguan)

  25. Breaking Block Boundaries: Anchor-based History-stable Decoding for Diffusion Large Language Models

    Apr 10, 2026Shun Zou, Yong Wang, Zehui Chen +4Diffusion Language Model DecodingDiffusion Model Inference Acceleration

    MoE Key Lab of BIPC, University of Science and Technology of China · AMAP, Alibaba Group

  26. DMax: Aggressive Parallel Decoding for dLLMs

    Apr 9, 2026Zigeng Chen, Gongfan Fang, Xinyin Ma +2Diffusion Language Model TrainingParallel Decoding for Diffusion Language Models

    National University of Singapore

  27. DualDiffusion: A Speculative Decoding Strategy for Masked Diffusion Models

    Apr 6, 2026Satyam Goyal, Kushal Patel, Tanush Mittal +1Diffusion Language Model InferenceSpeculative Decoding for Diffusion Language Models

    Department of Computer Science and Engineering, University of Michigan, Ann Arbor, MI, USA.

  28. Beyond Few-Step Inference: Accelerating Video Diffusion Transformer Model Serving with Inter-Request Caching Reuse

    Apr 6, 2026Hao Liu, Ye Huang, Chenghuan Huang +5Diffusion Model CachingDiffusion Model Inference Acceleration

    Sun Yat-sen University, China · Independent Researcher

  29. DiffSparse: Accelerating Diffusion Transformers with Learned Token Sparsity

    Apr 4, 2026Haowei Zhu, Ji Liu, Ziqiong Liu +4Diffusion Model Inference AccelerationDiffusion Models

    Advanced Micro Devices, Inc. · Tsinghua University · BNRist

  30. Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive Extrapolation

    Apr 3, 2026Hanshuai Cui, Zhiqing Tang, Zhi Yao +3Autoregressive Video GenerationDiffusion Model Inference Acceleration

    School of Artificial Intelligence, Beijing Normal University, Beijing, China · Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai, China · Shenzhen University of Advanced Technology, Shenzhen, China