Diffusion Model Caching

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 72

All topics

Motion-Aware Caching for Efficient Autoregressive Video Generation
May 3, 2026Jing Xu, Yuexiao Ma, Xuzhe Zheng +7Video Diffusion Models KV-Cache Management
1Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China · 2ByteDance · 3Max Planck Institute for Intelligent Systems, 4ELLIS Institute Tbingen, 5Tbingen AI Center
DARE: Diffusion Language Model Activation Reuse for Efficient Inference
May 1, 2026Natalia Frumkin, Bokun Wang, Hung-Yueh Chiang +3Self-Attention Diffusion Language Model Inference
Chandra Family Department of Electrical and Computer Engineering The University of Texas at Austin · Cornell University
Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models
Apr 29, 2026Zhirong Shen, Rui Huang, Jiacheng Liu +6Diffusion Transformer Diffusion Model Caching
Shanghai Jiao Tong University · University of Electronic Science and Technology of China · Shandong University +2
Accelerating Frequency Domain Diffusion Models with Error-Feedback Event-Driven Caching
Apr 24, 2026Dong Liu, Haisheng Wang, Yanxuan YuTime Series Generation Diffusion Model Caching
University of California, Los Angeles · Yale University · East China Normal University +1
X-Cache: Cross-Chunk Block Caching for Few-Step Autoregressive World Models Inference
Apr 22, 2026Yixiao Zeng, Jianlei Zheng, Chaoda Zheng +10Video Diffusion Models Diffusion Model Caching
AI Infra Team, XPeng Inc.
Efficient Video Diffusion Models: Advancements and Challenges
Apr 17, 2026Shitong Shao, Lichen Bai, Pengfei Wan +2Model Compression Video 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
Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration
Mar 2, 2026Jiaqi Han, Juntong Shi, Puheng Li +3Video Diffusion Models Diffusion-Based Image Generation
Stanford University · ByteDance
SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching
Feb 27, 2026Yasaman Haghighi, Alexandre AlahiVideo Diffusion Models Diffusion Model Caching
Ecole Polytechnique Fédérale de Lausanne (EPFL)
Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion
Feb 8, 2026Haodong Li, Shaoteng Liu, Zhe Lin +1Autoregressive Diffusion Long-Horizon Video Generation
UC San Diego · Adobe Research
FlashBlock: Attention Caching for Efficient Long-Context Block Diffusion
Feb 5, 2026Zhuokun Chen, Jianfei Cai, Bohan ZhuangVideo Diffusion Models Self-Attention
1Monash University · 2Zhejiang University
Window-Diffusion: Accelerating Diffusion Language Model Inference with Windowed Token Pruning and Caching
Jan 28, 2026Fengrui Zuo, Zhiwei Ke, Yiming Liu +3Diffusion Language Model Inference Token Pruning
School of Computer Science and Technology, University of Science and Technology of China · Suzhou Institute of Advanced Research, University of Science and Technology of China
CHIMERA: Adaptive Cache Injection and Semantic Anchor Prompting for Zero-shot Image Morphing with Morphing-oriented Metrics
Dec 8, 2025Dahyeon Kye, Jeahun Sung, Minkyu Jeon +1Diffusion Model Caching Diffusion-Based Image Editing
CMLab, Chung-Ang University · Princeton University

May 3, 2026, cs.CVJ/K move · Enter open · S save

Motion-Aware Caching for Efficient Autoregressive Video Generation

Jing Xu, Yuexiao Ma, Xuzhe Zheng, Xing Wang+6

1Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China · 2ByteDance · 3Max Planck Institute for Intelligent Systems, 4ELLIS Institute Tbingen, 5Tbingen AI Center

Video Diffusion Models KV-Cache Management Diffusion Model Caching Autoregressive Video Generation Diffusion Model Inference Acceleration

Open paper AskPDF arXiv

Autoregressive video generation paradigms offer theoretical promise for long video synthesis, yet their practical deployment is hindered by the computational burden of sequential iterative denoising. While cache reuse strategies can accelerate generation by skipping redundant denoising steps, existing methods rely on coarse-grained chunk-level skipping that fails to capture fine-grained pixel dynamics. This oversight is critical: pixels with high motion require more denoising steps to prevent error accumulation, while static pixels tolerate aggressive skipping. We formalize this insight theoretically by linking cache errors to residual instability, and propose MotionCache, a motion-aware cache framework that exploits inter-frame differences as a lightweight proxy for pixel-level motion characteristics. MotionCache employs a coarse-to-fine strategy: an initial warm-up phase establishes semantic coherence, followed by motion-weighted cache reuse that dynamically adjusts update frequencies per token. Extensive experiments on state-of-the-art models like SkyReels-V2 and MAGI-1 demonstrate that MotionCache achieves significant speedups of

\textbf{6.28}\times

and

\textbf{1.64}\times

respectively, while effectively preserving generation quality (VBench:

1\%\downarrow

and

0.01\%\downarrow

respectively). The code is available at https://github.com/ywlq/MotionCache.

Momentum

Related topics

Latest papers 72