English
Related papers

Related papers: ReHyAt: Recurrent Hybrid Attention for Video Diffu…

200 papers

Modern autoregressive models rely on attention, yet the Softmax full attention in Transformers scales quadratically with sequence length. Sliding Window Attention (SWA) achieves linear-time encoding/decoding by constraining the attention…

Machine Learning · Computer Science 2026-01-08 Jiaxu Liu , Yuhe Bai , Xiangyu Yin , Christos-Savvas Bouganis

The softmax content-based attention mechanism has proven to be very beneficial in many applications of recurrent neural networks. Nevertheless it suffers from two major computational limitations. First, its computations for an attention…

Machine Learning · Computer Science 2016-09-20 Alexandre de Brébisson , Pascal Vincent

Recent advances in video generation have made it possible to produce visually compelling videos, with wide-ranging applications in content creation, entertainment, and virtual reality. However, most existing diffusion transformer based…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Teng Hu , Jiangning Zhang , Zihan Su , Ran Yi

Video diffusion Transformer (DiT) models excel in generative quality but hit major computational bottlenecks when producing high-resolution, long-duration videos. The quadratic complexity of full attention leads to prohibitively high…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Chenlu Zhan , Wen Li , Chuyu Shen , Jun Zhang , Suhui Wu , Hao Zhang

Diffusion Transformers (DiTs) have emerged as a leading architecture for text-to-image synthesis, producing high-quality and photorealistic images. However, the quadratic scaling properties of the attention in DiTs hinder image generation…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Philipp Becker , Abhinav Mehrotra , Ruchika Chavhan , Malcolm Chadwick , Luca Morreale , Mehdi Noroozi , Alberto Gil Ramos , Sourav Bhattacharya

Contemporary diffusion models built upon U-Net or Diffusion Transformer (DiT) architectures have revolutionized image generation through transformer-based attention mechanisms. The prevailing paradigm has commonly employed self-attention…

Computer Vision and Pattern Recognition · Computer Science 2025-05-01 ZiYi Dong , Chengxing Zhou , Weijian Deng , Pengxu Wei , Xiangyang Ji , Liang Lin

The original softmax-based attention mechanism (regular attention) in the extremely successful Transformer architecture computes attention between $N$ tokens, each embedded in a $D$-dimensional head, with a time complexity of $O(N^2D)$.…

Machine Learning · Computer Science 2025-10-28 Armin Gerami , Ramani Duraiswami

This paper introduces ConvShareViT, a novel deep learning architecture that adapts Vision Transformers (ViTs) to the 4f free-space optical system. ConvShareViT replaces linear layers in multi-head self-attention (MHSA) and Multilayer…

Computer Vision and Pattern Recognition · Computer Science 2025-04-17 Riad Ibadulla , Thomas M. Chen , Constantino Carlos Reyes-Aldasoro

Transformers have significantly advanced AI and machine learning through their powerful attention mechanism. However, computing attention on long sequences can become a computational bottleneck. FlashAttention mitigates this by fusing the…

Hardware Architecture · Computer Science 2026-02-10 Kosmas Alexandridis , Giorgos Dimitrakopoulos

Video diffusion transformers have achieved remarkable progress in high-quality video generation, but remain computationally expensive due to the quadratic complexity of attention over high-dimensional video sequences. Recent acceleration…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Wenhao Sun , Rong-Cheng Tu , Yifu Ding , Zhao Jin , Jingyi Liao , Shunyu Liu , Dacheng Tao

Although transformer architectures have achieved state-of-the-art performance across diverse domains, their quadratic computational complexity with respect to sequence length remains a significant bottleneck, particularly for…

Computation and Language · Computer Science 2025-11-05 Zeyu Liu , Souvik Kundu , Lianghao Jiang , Anni Li , Srikanth Ronanki , Sravan Bodapati , Gourav Datta , Peter A. Beerel

Video generation has drawn significant interest recently, pushing the development of large-scale models capable of producing realistic videos with coherent motion. Due to memory constraints, these models typically generate short video…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Idan Kligvasser , Regev Cohen , George Leifman , Ehud Rivlin , Michael Elad

Efficient Transformers have been developed for long sequence modeling, due to their subquadratic memory and time complexity. Sparse Transformer is a popular approach to improving the efficiency of Transformers by restricting self-attention…

Machine Learning · Computer Science 2023-02-01 Aosong Feng , Irene Li , Yuang Jiang , Rex Ying

Video restoration aims at restoring multiple high-quality frames from multiple low-quality frames. Existing video restoration methods generally fall into two extreme cases, i.e., they either restore all frames in parallel or restore the…

Computer Vision and Pattern Recognition · Computer Science 2022-11-15 Jingyun Liang , Yuchen Fan , Xiaoyu Xiang , Rakesh Ranjan , Eddy Ilg , Simon Green , Jiezhang Cao , Kai Zhang , Radu Timofte , Luc Van Gool

Transformers have achieved state-of-the-art performance across various tasks, but suffer from a notable quadratic complexity in sequence length due to the attention mechanism. In this work, we propose MonarchAttention -- a novel approach to…

Machine Learning · Computer Science 2025-10-28 Can Yaras , Alec S. Xu , Pierre Abillama , Changwoo Lee , Laura Balzano

Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Anxhelo Diko , Danilo Avola , Marco Cascio , Luigi Cinque

The Transformer architecture has revolutionized deep learning, delivering the state-of-the-art performance in areas such as natural language processing, computer vision, and time series prediction. However, its core component,…

Machine Learning · Computer Science 2025-07-24 Haolin Jin , Mengbai Xiao , Yuan Yuan , Xiao Zhang , Dongxiao Yu , Guanghui Zhang , Haoliang Wang

Diffusion transformers have emerged as the mainstream paradigm for video generation models. However, the use of up to billions of parameters incurs significant computational costs. Quantization offers a promising solution by reducing memory…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Weilun Feng , Haotong Qin , Chuanguang Yang , Xiangqi Li , Han Yang , Yuqi Li , Zhulin An , Libo Huang , Michele Magno , Yongjun Xu

An essential component of modern recurrent sequence models is the forget gate. While Transformers do not have an explicit recurrent form, we show that a forget gate can be naturally incorporated into Transformers by down-weighting the…

Machine Learning · Computer Science 2025-04-02 Zhixuan Lin , Evgenii Nikishin , Xu Owen He , Aaron Courville

The computational cost of softmax-based attention in transformers limits their applicability to long-context tasks. Adaptive sparsity, of which $\alpha$-entmax attention is an example, offers a flexible data-dependent alternative, but…

Computation and Language · Computer Science 2025-06-10 Nuno Gonçalves , Marcos Treviso , André F. T. Martins