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. Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models

    Apr 2, 2026Liran Ringel, Ameen Ali, Yaniv RomanoDiffusion Language Model DecodingDiffusion Language Models

    Department of Computer Science, Technion – Israel Institute of Technology · Department of Electrical and Computer Engineering, Technion – Israel Institute of Technology · Blavatnik School of Computer Science and AI, Tel Aviv, Israel

  2. ZEUS: Accelerating Diffusion Models with Only Second-Order Predictor

    Apr 2, 2026Yixiao Wang, Ting Jiang, Zishan Shao +6Diffusion Model Inference AccelerationDiffusion-Based Image Generation

    Department of Computer Science, Duke University, Durham, NC, USA · Department of Statistical Science, Duke University, Durham, NC, USA · Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA

  3. EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation

    Mar 30, 2026Sravanth Kodavanti, Manjunath Arveti, Sowmya Vajrala +2Diffusion TransformerDiffusion-Based Image Generation

    Samsung Research Institute Bangalore, India

  4. Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting

    Mar 30, 2026Zhen Zou, Xiaoxiao Ma, Mingde Yao +3Autoregressive DiffusionVisual Autoregressive Models

    University of Science and Technology of China · The Chinese University of Hong Kong, MMLAB · JD Explore Academy +1

  5. InstaVSR: Taming Diffusion for Efficient and Temporally Consistent Video Super-Resolution

    Mar 27, 2026Jintong Hu, Bin Chen, Zhenyu Hu +3Video Super-ResolutionDiffusion Models

    Insta360 Research · Peking University · Wuhan University

  6. DRiffusion: Draft-and-Refine Process Parallelizes Diffusion Models with Ease

    Mar 26, 2026Runsheng Bai, Chengyu Zhang, Yangdong DengDiffusion Model SamplingDiffusion Model Inference Acceleration

    CSAIL, MIT · IST, Nanjing University · School of Software, Tsinghua University; FuturististAI Lab, Shanghai Tsinghua International Innovation Center

  7. S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation

    Mar 26, 2026Ligong Han, Hao Wang, Han Gao +2Speculative Decoding for Diffusion Language ModelsDiffusion Language Model Decoding

    Red Hat AI Innovation · MIT-IBM Watson AI Lab · Iowa State University +1

  8. FODMP: Fast One-Step Diffusion of Movement Primitives Generation for Time-Dependent Robot Actions

    Mar 25, 2026Xirui Shi, Arya Ebrahimi, Yi Hu +1Robot Motion GenerationDiffusion Models for Motion Generation

    Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Alberta, Canada. · Jun Jin is also with the Alberta Machine Intelligence Institute(Amii), Edmonton, Alberta, Canada.

  9. Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration

    Mar 25, 2026Danil Tokhchukov, Aysel Mirzoeva, Andrey Kuznetsov +1Diffusion TransformerT2I Diffusion Models

    MSU · FusionBrain Lab, AXXX

  10. Polynomial Speedup in Diffusion Models with the Multilevel Euler-Maruyama Method

    Mar 25, 2026Arthur JacotDiffusion Model Inference AccelerationDiffusion Sampling

  11. Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep

    Mar 25, 2026Tianyi Liu, Ye Lu, Linfeng Zhang +5Diffusion-Based Video EditingDiffusion Model Inference Acceleration

    Nanyang Technological University · Shanghai Jiao Tong University · The Hong Kong Polytechnic University

  12. Tiny Inference-Time Scaling with Latent Verifiers

    Mar 23, 2026Davide Bucciarelli, Evelyn Turri, Lorenzo Baraldi +3Inference-Time ScalingDiffusion Models

    University of Modena and Reggio Emilia, Italy · University of Pisa, Italy

  13. MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding

    Mar 23, 2026Hejun Dong, Junbo Niu, Bin Wang +3Optical Character RecognitionDiffusion Language Model Decoding

    Shanghai Artificial Intelligence Laboratory, OpenDataLab · Peking University

  14. WorldCache: Content-Aware Caching for Accelerated Video World Models

    Mar 23, 2026Umair Nawaz, Ahmed Heakl, Ufaq Khan +3Diffusion Model CachingDiffusion Model Inference Acceleration

    Mohamed bin Zayed University of Artificial Intelligence, UAE · Linköping University, Sweden

  15. Confidence-Based Decoding is Provably Efficient for Diffusion Language Models

    Mar 23, 2026Changxiao Cai, Gen LiDiffusion Language Model DecodingDiffusion Model Inference Acceleration

    Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, USA · Department of Statistics and Data Science, The Chinese University of Hong Kong, Hong Kong

  16. DA-VAE: Plug-in Latent Compression for Diffusion via Detail Alignment

    Mar 23, 2026Xin Cai, Zhiyuan You, Zhoutong Zhang +1Diffusion-Based Image GenerationDiffusion Model Compression

    Multimedia Laboratory, The Chinese University of Hong Kong · Shanghai AI Laboratory · Adobe NextCam +1

  17. Three Creates All: You Only Sample 3 Steps

    Mar 23, 2026Yuren Cai, Guangyi Wang, Zongqing Li +3Few-Step Diffusion SamplingDiffusion Model Inference Acceleration

    School of Informatics, Xiamen University · School of Artificial Intelligence, Shenzhen Polytechnic University · Algorithm Research Department, Truesight

  18. Efficient Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution

    Mar 22, 2026Yu-Shan Tai, An-Yeu, WuDiffusion Model SamplingDiffusion Sampling

    Andy · Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan

  19. 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

  20. Accelerating Diffusion Decoders via Multi-Scale Sampling and One-Step Distillation

    Mar 20, 2026Chuhan Wang, Hao ChenImage TokenizationDiffusion Model Inference Acceleration

    Carnegie Mellon University

  21. Spectrally-Guided Diffusion Noise Schedules

    Mar 19, 2026Carlos Esteves, Ameesh MakadiaDiffusion-Based Image GenerationDiffusion Timestep Scheduling

    Google Research.

  22. Attention-Based Sampler for Diffusion Language Models

    Mar 18, 2026Yuyan Zhou, Kai Syun Hou, Weiyu Chen +1Diffusion SamplingDiffusion Language Model Decoding

    Department of Computer Science and Engineering, The Hong Kong University of Science and Technology

  23. D3D^3-RSMDE: 40×\times Faster and High-Fidelity Remote Sensing Monocular Depth Estimation

    Mar 17, 2026Ruizhi Wang, Weihan Li, Zunlei Feng +5Monocular Depth EstimationDiffusion Model Inference Acceleration

    School of Software Technology, Zhejiang University · State Key Laboratory of Blockchain and Data Security, Zhejiang University · Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security +2

  24. Flash-Unified: A Training-Free and Task-Aware Acceleration Framework for Native Unified Models

    Mar 16, 2026Junlong Ke, Zichen Wen, Boxue Yang +6Efficient Multimodal InferenceUnified Multimodal Models

    Tsinghua University · Shanghai Jiao Tong University · Shanghai AI Laboratory +3

  25. Chain-of-Trajectories: Unlocking the Intrinsic Generative Optimality of Diffusion Models via Graph-Theoretic Planning

    Mar 16, 2026Ping Chen, Xiang Liu, Xingpeng Zhang +7Diffusion SamplingDiffusion-Based Planning

    Data Science & Artificial Intelligence Research Institute, China Unicom · Unicom Data Intelligence, China Unicom · School of Computer Science and Software Engineering, Southwest Petroleum University +2

  26. LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion

    Mar 15, 2026Zengqun Zhao, Ziquan Liu, Yu Cao +5Video Diffusion ModelsInference-Time Scaling

    Queen Mary University of London · Huawei R&D UK · Imperial College London

  27. Early Failure Detection and Intervention in Video Diffusion Models

    Mar 15, 2026Kwon Byung-Ki, Sohwi Lim, Nam Hyeon-Woo +2Video Diffusion ModelsT2V Generation

    Grad. School of Artificial Intelligence, POSTECH · School of Electrical Engineering, KAIST · Dept. of Electrical Engineering, POSTECH +1

  28. TMPDiff: Temporal Mixed-Precision for Diffusion Models

    Mar 14, 2026Basile Lewandowski, Simon Kurz, Aditya Shankar +3Diffusion Model QuantizationDiffusion Model Inference Acceleration

    University of Neuchâtel, Switzerland · TU Dortmund University, Germany · LAMARR Institute, Germany +2

  29. Amortizing Trajectory Diffusion with Keyed Drift Fields

    Mar 14, 2026Gokul Puthumanaillam, Melkior OrnikTrajectory GenerationDiffusion-Based Planning

    University of Illinois Urbana-Champaign

  30. DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression

    Mar 13, 2026Junqi Shi, Ming Lu, Xingchen Li +3Learned Image CompressionGenerative Image Compression

    School of Electronic Science and Engineering, Nanjing University, Nanjing 210023, China