English
Related papers

Related papers: Accelerating Rectified Flow Models via Trajectory-…

200 papers

Autoregressive models, often built on Transformer architectures, represent a powerful paradigm for generating ultra-long videos by synthesizing content in sequential chunks. However, this sequential generation process is notoriously slow.…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Yuexiao Ma , Xuzhe Zheng , Jing Xu , Xiwei Xu , Feng Ling , Xiawu Zheng , Huafeng Kuang , Huixia Li , Xing Wang , Xuefeng Xiao , Fei Chao , Rongrong Ji

Diffusion Transformers (DiTs) have achieved state-of-the-art performance in generative modeling, yet their high computational cost hinders real-time deployment. While feature caching offers a promising training-free acceleration solution by…

Computer Vision and Pattern Recognition · Computer Science 2026-02-16 Fanpu Cao , Yaofo Chen , Zeng You , Wei Luo

Efficient video generation models are increasingly vital for multimedia synthetic content generation. Leveraging the Transformer architecture and the diffusion process, video DiT models have emerged as a dominant approach for high-quality…

Graphics · Computer Science 2026-02-27 Yuanxin Wei , Lansong Diao , Bujiao Chen , Shenggan Cheng , Zhengping Qian , Wenyuan Yu , Nong Xiao , Wei Lin , Jiangsu Du

Diffusion models have recently gained unprecedented attention in the field of image synthesis due to their remarkable generative capabilities. Notwithstanding their prowess, these models often incur substantial computational costs,…

Computer Vision and Pattern Recognition · Computer Science 2023-12-11 Xinyin Ma , Gongfan Fang , Xinchao Wang

High computational costs and slow inference hinder the practical application of video generation models. While prior works accelerate the generation process through feature caching, they often suffer from notable quality degradation. In…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Jiangshan Wang , Kang Zhao , Jiayi Guo , Jiayu Wang , Hang Guo , Chenyang Zhu , Xiu Li , Xiangyu Yue

Diffusion models achieve remarkable generative quality, but computational overhead scales with step count, model depth, and sequence length. Feature caching is effective since adjacent timesteps yield highly similar features. However, an…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Tingyan Wen , Haoyu Li , Yihuang Chen , Xing Zhou , Lifei Zhu , Xueqian Wang

Feature caching approaches accelerate diffusion transformers (DiTs) by storing the output features of computationally expensive modules at certain timesteps, and exploiting them for subsequent steps to reduce redundant computations. Recent…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Byunggwan Son , Jeimin Jeon , Jeongwoo Choi , Bumsub Ham

Diffusion models have emerged as a powerful paradigm for generative tasks such as image synthesis and video generation, with Transformer architectures further enhancing performance. However, the high computational cost of diffusion…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Huanpeng Chu , Wei Wu , Guanyu Fen , Yutao Zhang

Diffusion-based world models have shown strong potential for unified world simulation, but the iterative denoising remains too costly for interactive use and long-horizon rollouts. While feature caching can accelerate inference without…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Weilun Feng , Guoxin Fan , Haotong Qin , Chuanguang Yang , Mingqiang Wu , Yuqi Li , Xiangqi Li , Zhulin An , Libo Huang , Dingrui Wang , Longlong Liao , Michele Magno , Yongjun Xu

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…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Jing Xu , Yuexiao Ma , Xuzhe Zheng , Xing Wang , Shiwei Liu , Chenqian Yan , Xiawu Zheng , Rongrong Ji , Fei Chao , Songwei Liu

Existing acceleration techniques for video diffusion models often rely on uniform heuristics or time-embedding variants to skip timesteps and reuse cached features. These approaches typically require extensive calibration with curated…

Computer Vision and Pattern Recognition · Computer Science 2025-11-06 Zehong Ma , Longhui Wei , Feng Wang , Shiliang Zhang , Qi Tian

Diffusion models demonstrate outstanding performance in image generation, but their multi-step inference mechanism requires immense computational cost. Previous works accelerate inference by leveraging layer or token cache techniques to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Haowei Zhu , Ji Liu , Ziqiong Liu , Dong Li , Junhai Yong , Bin Wang , Emad Barsoum

Diffusion Transformers (DiT) are powerful generative models but remain computationally intensive due to their iterative structure and deep transformer stacks. To alleviate this inefficiency, we propose \textbf{FastCache}, a…

Machine Learning · Computer Science 2026-03-30 Dong Liu , Yanxuan Yu , Jiayi Zhang , Yifan Li , Ben Lengerich , Ying Nian Wu

Diffusion models are a strong backbone for visual generation, but their inherently sequential denoising process leads to slow inference. Previous methods accelerate sampling by caching and reusing intermediate outputs based on feature…

Computer Vision and Pattern Recognition · Computer Science 2026-03-25 Jiwoo Chung , Sangeek Hyun , MinKyu Lee , Byeongju Han , Geonho Cha , Dongyoon Wee , Youngjun Hong , Jae-Pil Heo

Diffusion transformers have shown significant effectiveness in both image and video synthesis at the expense of huge computation costs. To address this problem, feature caching methods have been introduced to accelerate diffusion…

Machine Learning · Computer Science 2025-02-20 Chang Zou , Xuyang Liu , Ting Liu , Siteng Huang , Linfeng Zhang

Recently, Diffusion Transformers (DiTs) have emerged as a dominant architecture in video generation, surpassing U-Net-based models in terms of performance. However, the enhanced capabilities of DiTs come with significant drawbacks,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Junyi Wu , Zhiteng Li , Zheng Hui , Yulun Zhang , Linghe Kong , Xiaokang Yang

Diffusion models have achieved remarkable success in content generation but often incur prohibitive computational costs due to iterative sampling. Recent feature caching methods accelerate inference via temporal extrapolation, yet can…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Liang Feng , Shikang Zheng , Jiacheng Liu , Yuqi Lin , Qinming Zhou , Peiliang Cai , Xinyu Wang , Junjie Chen , Chang Zou , Yue Ma , Linfeng Zhang

Text-to-Video applications receive increasing attention from the public. Among these, diffusion models have emerged as the most prominent approach, offering impressive quality in visual content generation. However, it still suffers from…

Multimedia · Computer Science 2025-01-09 Desen Sun , Henry Tian , Tim Lu , Sihang Liu

Diffusion transformer (DiT) models have achieved remarkable success in image generation, thanks for their exceptional generative capabilities and scalability. Nonetheless, the iterative nature of diffusion models (DMs) results in high…

Computer Vision and Pattern Recognition · Computer Science 2025-05-12 Zhiyuan Chen , Keyi Li , Yifan Jia , Le Ye , Yufei Ma

Flow Matching models achieve state-of-the-art image generation quality but incur substantial inference cost due to iterative denoising through large Transformer networks. We observe that different layer groups within a Transformer exhibit…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Guandong Li