English
Related papers

Related papers: CLEAR: Conv-Like Linearization Revs Pre-Trained Di…

200 papers

Transformers have driven remarkable breakthroughs in natural language processing and computer vision, yet their standard attention mechanism still imposes O(N^2) complexity, hindering scalability to longer sequences. We introduce…

Machine Learning · Computer Science 2026-01-06 Yoshihiro Yamada

Recently, large efforts have been made to design efficient linear-complexity visual Transformers. However, current linear attention models are generally unsuitable to be deployed in resource-constrained mobile devices, due to suffering from…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Yuan Zhou , Qingshan Xu , Jiequan Cui , Junbao Zhou , Jing Zhang , Richang Hong , Hanwang Zhang

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

Pre-trained language models (e.g., BERT (Devlin et al., 2018) and its variants) have achieved remarkable success in varieties of NLP tasks. However, these models usually consist of hundreds of millions of parameters which brings challenges…

Computation and Language · Computer Science 2020-04-07 Wenhui Wang , Furu Wei , Li Dong , Hangbo Bao , Nan Yang , Ming Zhou

Text-guided image generation and editing using diffusion models have achieved remarkable advancements. Among these, tuning-free methods have gained attention for their ability to perform edits without extensive model adjustments, offering…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Wenyi Mo , Tianyu Zhang , Yalong Bai , Bing Su , Ji-Rong Wen

Diffusion Transformers (DiTs) with billions of model parameters form the backbone of popular image and video generation models like DALL.E, Stable-Diffusion and SORA. Though these models are necessary in many low-latency applications like…

Computer Vision and Pattern Recognition · Computer Science 2025-02-21 Vignesh Sundaresha

Diffusion Transformers (DiTs) achieve state-of-the-art performance in text-to-image synthesis but remain computationally expensive due to the iterative nature of denoising and the quadratic cost of global attention. In this work, we observe…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Bowen Lin , Fanjiang Ye , Yihua Liu , Zhenghui Guo , Boyuan Zhang , Weijian Zheng , Yufan Xu , Tiancheng Xing , Yuke Wang , Chengming Zhang

Diffusion Transformers (DiTs) have achieved state-of-the-art (SOTA) image generation quality but suffer from high latency and memory inefficiency, making them difficult to deploy on resource-constrained devices. One major efficiency…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Haoran You , Connelly Barnes , Yuqian Zhou , Yan Kang , Zhenbang Du , Wei Zhou , Lingzhi Zhang , Yotam Nitzan , Xiaoyang Liu , Zhe Lin , Eli Shechtman , Sohrab Amirghodsi , Yingyan Celine Lin

Diffusion language models (dLMs) have emerged as a promising paradigm that enables parallel, non-autoregressive generation, but their learning efficiency lags behind that of autoregressive (AR) language models when trained from scratch. To…

Despite recent advances, diffusion-based text-to-image models still struggle with accurate text rendering. Several studies have proposed fine-tuning or training-free refinement methods for accurate text rendering. However, the critical…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Kanghyun Baek , Sangyub Lee , Jin Young Choi , Jaewoo Song , Daemin Park , Jooyoung Choi , Chaehun Shin , Bohyung Han , Sungroh Yoon

Video diffusion models (DMs) have enabled high-quality video synthesis. However, their computation costs scale quadratically with sequence length because self-attention has quadratic complexity. While linear attention lowers the cost, fully…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Yushi Huang , Xingtong Ge , Ruihao Gong , Chengtao Lv , Jun Zhang

Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Transformer hinders its applicability to high-resolution images. Existing methods mitigate this…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Yuang Ai , Huaibo Huang , Tao Wu , Qihang Fan , Ran He

Diffusion Transformers (DiT) have attracted significant attention in research. However, they suffer from a slow convergence rate. In this paper, we aim to accelerate DiT training without any architectural modification. We identify the…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Jingfeng Yao , Wang Cheng , Wenyu Liu , Xinggang Wang

Language Models pretrained on large textual data have been shown to encode different types of knowledge simultaneously. Traditionally, only the features from the last layer are used when adapting to new tasks or data. We put forward that,…

Computation and Language · Computer Science 2024-05-08 Muhammad ElNokrashy , Badr AlKhamissi , Mona Diab

The attention mechanism is an important reason for the success of transformers. It relies on computing pairwise relations between tokens. To reduce the high computational cost of standard quadratic attention, linear attention has been…

Artificial Intelligence · Computer Science 2026-02-13 Hanno Ackermann , Hong Cai , Mohsen Ghafoorian , Amirhossein Habibian

Recent research arXiv:2410.15027 has explored the use of diffusion transformers (DiTs) for task-agnostic image generation by simply concatenating attention tokens across images. However, despite substantial computational resources, the…

Computer Vision and Pattern Recognition · Computer Science 2024-11-06 Lianghua Huang , Wei Wang , Zhi-Fan Wu , Yupeng Shi , Huanzhang Dou , Chen Liang , Yutong Feng , Yu Liu , Jingren Zhou

The self-attention mechanism has been a key factor in the advancement of vision Transformers. However, its quadratic complexity imposes a heavy computational burden in high-resolution scenarios, restricting the practical application.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Dongchen Han , Tianyu Li , Ziyi Wang , Gao Huang

The quadratic computational cost of the self-attention mechanism is a primary challenge in scaling Transformer models. While attention sparsity is widely studied as a technique to improve computational efficiency, it is almost universally…

Computation and Language · Computer Science 2025-08-11 Sagar Gandhi , Vishal Gandhi

Recent advances in diffusion models have demonstrated remarkable capabilities in video generation. However, the computational intensity remains a significant challenge for practical applications. While feature caching has been proposed to…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Xuran Ma , Yexin Liu , Yaofu Liu , Xianfeng Wu , Mingzhe Zheng , Zihao Wang , Ser-Nam Lim , Harry Yang

Vision Transformers (ViTs) have delivered remarkable progress through global self-attention, yet their quadratic complexity can become prohibitive for high-resolution inputs. In this work, we present ViT-Linearizer, a cross-architecture…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Guoyizhe Wei , Rama Chellappa
‹ Prev 1 3 4 5 6 7 10 Next ›