English
Related papers

Related papers: TaoCache: Structure-Maintained Video Generation Ac…

200 papers

Autoregressive video diffusion models enable streaming generation, opening the door to long-form synthesis, video world models, and interactive neural game engines. However, their core attention layers become a major bottleneck at inference…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Dvir Samuel , Issar Tzachor , Matan Levy , Micahel Green , Gal Chechik , Rami Ben-Ari

Diffusion-based video generation has advanced substantially in visual fidelity and temporal coherence, but practical deployment remains limited by the quadratic complexity of full attention. Training-free sparse attention is attractive…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Xuzhe Zheng , Yuexiao Ma , Jing Xu , Xiawu Zheng , Rongrong Ji , Fei Chao

Diffusion Transformers (DiTs) have demonstrated remarkable performance in visual generation tasks. However, their low inference speed limits their deployment in low-resource applications. Recent training-free approaches exploit the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Xiaoliu Guan , Lielin Jiang , Hanqi Chen , Xu Zhang , Jiaxing Yan , Guanzhong Wang , Yi Liu , Zetao Zhang , Yu Wu

Diffusion Transformers (DiTs) excel in generative tasks but face practical deployment challenges due to high inference costs. Feature caching, which stores and retrieves redundant computations, offers the potential for acceleration.…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Yushi Huang , Zining Wang , Ruihao Gong , Jing Liu , Xinjie Zhang , Jinyang Guo , Xianglong Liu , Jun Zhang

Despite achieving state-of-the-art generation quality, diffusion models are hindered by the substantial computational burden of their iterative sampling process. While feature caching techniques achieve effective acceleration at higher step…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Benlei Cui , Shaoxuan He , Bukun Huang , Zhizeng Ye , Yunyun Sun , Longtao Huang , Hui Xue , Yang Yang , Jingqun Tang , Zhou Zhao , Haiwen Hong

Personalized image generation requires text-to-image generative models that capture the core features of a reference subject to allow for controlled generation across different contexts. Existing methods face challenges due to complex…

Computer Vision and Pattern Recognition · Computer Science 2024-11-28 Emanuele Aiello , Umberto Michieli , Diego Valsesia , Mete Ozay , Enrico Magli

Streaming video understanding requires processing unbounded video streams with limited memory and computation, posing two key challenges. First, continuously constructing new and evicting old key-value(KV) caches is required for unbounded…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Zhanzhong Pang , Dibyadip Chatterjee , Fadime Sener , Angela Yao

Diffusion models are widely recognized for generating high-quality and diverse images, but their poor real-time performance has led to numerous acceleration works, primarily focusing on UNet-based structures. With the more successful…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Pengtao Chen , Mingzhu Shen , Peng Ye , Jianjian Cao , Chongjun Tu , Christos-Savvas Bouganis , Yiren Zhao , Tao Chen

Current video captioning methods usually use an encoder-decoder structure to generate text autoregressively. However, autoregressive methods have inherent limitations such as slow generation speed and large cumulative error. Furthermore,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Junbo Wang , Liangyu Fu , Yuke Li , Yining Zhu , Ya Jing , Xuecheng Wu , Jiangbin Zheng

Autoregressive video diffusion models support real-time synthesis but suffer from error accumulation and context loss over long horizons. We discover that attention heads in AR video diffusion transformers serve functionally distinct roles…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Jiahao Tian , Yiwei Wang , Gang Yu , Chi Zhang

Video Diffusion Transformers have revolutionized high-fidelity video generation but suffer from the massive computational burden of self-attention. While sparse attention provides a promising acceleration solution, existing methods…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Wentai Zhang , Ronghui Xi , Shiyao Peng , Jiayu Huang , Haoran Luo , Zichen Tang , Haihong E

Autoregressive (AR) video generation has emerged as a promising paradigm for long-horizon video synthesis, where each frame is generated conditioned on previously generated tokens. To accelerate inference, the KV cache is used to avoid…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Jiayi Luo , Qiyan Liu , Tengyang Wang , JunHao Liu , Jiayu Chen , Cong Wang , Hanxin Zhu , Chen Gao , Xiaobin Hu , Qingyun Sun , Zhibo Chen

We present LeMiCa, a training-free and efficient acceleration framework for diffusion-based video generation. While existing caching strategies primarily focus on reducing local heuristic errors, they often overlook the accumulation of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-12 Huanlin Gao , Ping Chen , Fuyuan Shi , Chao Tan , Zhaoxiang Liu , Fang Zhao , Kai Wang , Shiguo Lian

We present DeepCache, a principled cache design for deep learning inference in continuous mobile vision. DeepCache benefits model execution efficiency by exploiting temporal locality in input video streams. It addresses a key challenge…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Mengwei Xu , Mengze Zhu , Yunxin Liu , Felix Xiaozhu Lin , Xuanzhe Liu

Video diffusion models have recently enabled high-quality video generation with ViT-based architectures, but remain computationally intensive because generation requires attention computation over long spatiotemporal sequences. Token…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Sheng Li , Yang Sui , Junhao Ran , Bo Yuan , Yue Dai , Xulong Tang

Autoregressive (AR) video diffusion models enable long-form video generation but remain expensive due to repeated multi-step denoising. Existing training-free acceleration methods rely on binary cache-or-recompute decisions, overlooking…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Hanshuai Cui , Zhiqing Tang , Zhi Yao , Fanshuai Meng , Weijia Jia , Wei Zhao

Diffusion Transformers (DiT) have revolutionized high-fidelity image and video synthesis, yet their computational demands remain prohibitive for real-time applications. To solve this problem, feature caching has been proposed to accelerate…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Jiacheng Liu , Chang Zou , Yuanhuiyi Lyu , Junjie Chen , Linfeng Zhang

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

Diffusion models have recently revolutionized the field of image synthesis due to their ability to generate photorealistic images. However, one of the major drawbacks of diffusion models is that the image generation process is costly. A…

Vision-Language-Action (VLA) models enable generalist robotic manipulation but suffer from high inference latency. This bottleneck stems from the massive number of visual tokens processed by large language backbones. Existing methods either…

Robotics · Computer Science 2026-03-12 Yuquan Li , Lianjie Ma , Han Ding , Lijun Zhu