English
Related papers

Related papers: Bidirectional Sparse Attention for Faster Video Di…

200 papers

Transformers are becoming the mainstream solutions for various tasks like NLP and Computer vision. Despite their success, the high complexity of the attention mechanism hinders them from being applied to latency-sensitive tasks. Tremendous…

Machine Learning · Computer Science 2022-03-02 Zhaodong Chen , Yuying Quan , Zheng Qu , Liu Liu , Yufei Ding , Yuan Xie

Diffusion Transformer (DiT), a promising diffusion model for visual generation, demonstrates impressive performance but incurs significant computational overhead. Intriguingly, analysis of pre-trained DiT models reveals that global…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Yuang Ai , Qihang Fan , Xuefeng Hu , Zhenheng Yang , Ran He , Huaibo Huang

Diffusion Transformer (DiT), an emerging diffusion model for image generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs stem from the static inference…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Wangbo Zhao , Yizeng Han , Jiasheng Tang , Kai Wang , Yibing Song , Gao Huang , Fan Wang , Yang You

The Diffusion Transformer (DiT) architecture is the state-of-the-art paradigm for high-fidelity image generation, underpinning models like Stable Diffusion-3 and FLUX.1. However, deploying these models on resource-constrained mobile devices…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Kunpeng Du , Haizhen Xie , Sen Lu , Lei Yu , Binglei Bao , Huaao Tang , Chuntao Liu , Hao Wu , Yang Zhao , Zhicai Huang , Heyuan Gao , Zhijun Tu , Jie Hu , Xinghao Chen

Multi-Modal Diffusion Transformers (DiTs) demonstrate exceptional capabilities in visual synthesis, yet their deployment remains constrained by substantial computational demands. To alleviate this bottleneck, many sparsity-based…

Machine Learning · Computer Science 2025-10-01 Liang Qiao , Yue Dai , Yeqi Huang , Hongyu Kan , Jun Shi , Hong An

Domain Adaptation (DA) aims to leverage the knowledge learned from a source domain with ample labeled data to a target domain with unlabeled data only. Most existing studies on DA contribute to learning domain-invariant feature…

Computer Vision and Pattern Recognition · Computer Science 2022-10-04 Xiyu Wang , Pengxin Guo , Yu Zhang

The adoption of long context windows has become a standard feature in Large Language Models (LLMs), as extended contexts significantly enhance their capacity for complex reasoning and broaden their applicability across diverse scenarios.…

Computation and Language · Computer Science 2026-05-20 Wenxuan Li , Chengruidong Zhang , Huiqiang Jiang , Yucheng Li , Yuqing Yang , Lili Qiu

Long-form speech recognition is an application area of increasing research focus. ASR models based on multi-head attention (MHA) are ill-suited to long-form ASR because of their quadratic complexity in sequence length. We build on recent…

Computation and Language · Computer Science 2025-06-25 Martin Ratajczak , Jean-Philippe Robichaud , Jennifer Drexler Fox

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

Current video deblurring methods have limitations in recovering high-frequency information since the regression losses are conservative with high-frequency details. Since Diffusion Models (DMs) have strong capabilities in generating…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Chen Rao , Guangyuan Li , Zehua Lan , Jiakai Sun , Junsheng Luan , Wei Xing , Lei Zhao , Huaizhong Lin , Jianfeng Dong , Dalong Zhang

In this paper, we investigate how to convert a pre-trained Diffusion Transformer (DiT) into a linear DiT, as its simplicity, parallelism, and efficiency for image generation. Through detailed exploration, we offer a suite of ready-to-use…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Jiahao Wang , Ning Kang , Lewei Yao , Mengzhao Chen , Chengyue Wu , Songyang Zhang , Shuchen Xue , Yong Liu , Taiqiang Wu , Xihui Liu , Kaipeng Zhang , Shifeng Zhang , Wenqi Shao , Zhenguo Li , Ping Luo

Recent progress in transformer-based architectures has demonstrated remarkable success in video generation tasks. However, the quadratic complexity of full attention mechanisms remains a critical bottleneck, particularly for high-resolution…

Recently Transformers have provided state-of-the-art performance in sparse matching, crucial to realize high-performance 3D vision applications. Yet, these Transformers lack efficiency due to the quadratic computational complexity of their…

Computer Vision and Pattern Recognition · Computer Science 2022-04-25 Suwichaya Suwanwimolkul , Satoshi Komorita

Sparsifying the Transformer has garnered considerable interest, as training the Transformer is very computationally demanding. Prior efforts to sparsify the Transformer have either used a fixed pattern or data-driven approach to reduce the…

Machine Learning · Computer Science 2023-09-25 Bokyeong Yoon , Yoonsang Han , Gordon Euhyun Moon

Diffusion models have gained attention for their success in modeling complex distributions, achieving impressive perceptual quality in SR tasks. However, existing diffusion-based SR methods often suffer from high computational costs,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Rui Qin , Qijie Wang , Ming Sun , Haowei Zhu , Chao Zhou , Bin Wang

Due to the auto-regressive nature of current video large language models (Video-LLMs), the inference latency increases as the input sequence length grows, posing challenges for the efficient processing of video sequences that are usually…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Xuan Zhang , Cunxiao Du , Sicheng Yu , Jiawei Wu , Fengzhuo Zhang , Wei Gao , Qian Liu

An efficient attention implementation is essential for large models due to its quadratic time complexity. Fortunately, attention commonly exhibits sparsity, i.e., many values in the attention map are near zero, allowing for the omission of…

Machine Learning · Computer Science 2025-11-20 Jintao Zhang , Chendong Xiang , Haofeng Huang , Jia Wei , Haocheng Xi , Jun Zhu , Jianfei Chen

Video object removal and inpainting are critical tasks in the fields of computer vision and multimedia processing, aimed at restoring missing or corrupted regions in video sequences. Traditional methods predominantly rely on flow-based…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Jie Liu , Zheng Hui

The quadratic complexity of the attention mechanism severely limits the context scalability of Video Diffusion Transformers (DiTs). We find that the highly sparse spatio-temporal attention patterns exhibited in Video DiTs can be naturally…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Cheng Liang , Haoxian Chen , Liang Hou , Qi Fan , Gangshan Wu , Xin Tao , Limin Wang

The quadratic complexity of self attention in Transformer based LLMs renders long context inference prohibitively expensive. While Sliding Window Attention (SWA), the simplest sparse attention pattern, offers a linear complexity…

Computation and Language · Computer Science 2026-03-27 Yijiong Yu , Jiale Liu , Qingyun Wu , Huazheng Wang , Ji Pei