English
Related papers

Related papers: SageAttention: Accurate 8-Bit Attention for Plug-a…

200 papers

We describe an efficient hierarchical method to compute attention in the Transformer architecture. The proposed attention mechanism exploits a matrix structure similar to the Hierarchical Matrix (H-Matrix) developed by the numerical…

Machine Learning · Computer Science 2021-07-27 Zhenhai Zhu , Radu Soricut

We introduce exclusive self attention (XSA), a simple modification of self attention (SA) that improves Transformer's sequence modeling performance. The key idea is to constrain attention to capture only information orthogonal to the…

Machine Learning · Computer Science 2026-03-11 Shuangfei Zhai

Since their introduction the Trasformer architectures emerged as the dominating architectures for both natural language processing and, more recently, computer vision applications. An intrinsic limitation of this family of "fully-attentive"…

Machine Learning · Computer Science 2023-03-16 Carmelo Scribano , Giorgia Franchini , Marco Prato , Marko Bertogna

Transformer models have achieved remarkable results in a wide range of applications. However, their scalability is hampered by the quadratic time and memory complexity of the self-attention mechanism concerning the sequence length. This…

Machine Learning · Computer Science 2024-02-27 Yury Nahshan , Joseph Kampeas , Emir Haleva

Transformer models have revolutionized natural language processing, achieving state-of-the-art performance and demonstrating remarkable scalability. However, their memory demands, particularly due to maintaining full context in memory, pose…

Computation and Language · Computer Science 2025-11-04 Juan Gabriel Kostelec , Qinghai Guo

The self-attention mechanism is the key to the success of transformers in recent Large Language Models (LLMs). However, the quadratic computational cost $O(n^2)$ in the input sequence length $n$ is a notorious obstacle for further…

Machine Learning · Computer Science 2024-10-17 Yingyu Liang , Heshan Liu , Zhenmei Shi , Zhao Song , Zhuoyan Xu , Junze Yin

Transformers have shown superior performance on various vision tasks. Their large receptive field endows Transformer models with higher representation power than their CNN counterparts. Nevertheless, simply enlarging the receptive field…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Zhuofan Xia , Xuran Pan , Shiji Song , Li Erran Li , Gao Huang

Attention is an effective mechanism to improve the deep model capability. Squeeze-and-Excite (SE) introduces a light-weight attention branch to enhance the network's representational power. The attention branch is gated using the Sigmoid…

Computer Vision and Pattern Recognition · Computer Science 2021-03-25 Chunjie Luo , Jianfeng Zhan , Tianshu Hao , Lei Wang , Wanling Gao

Transformers have demonstrated outstanding performance across a wide range of tasks, owing to their self-attention mechanism, but they are highly energy-consuming. Spiking Neural Networks have emerged as a promising energy-efficient…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Yufei Guo , Xiaode Liu , Yuanpei Chen , Weihang Peng , Yuhan Zhang , Zhe Ma

Transformer has become the dominant architecture for sequence modeling, yet a detailed understanding of how its structural parameters influence expressive power remains limited. In this work, we study the approximation properties of…

Machine Learning · Computer Science 2026-04-01 Penghao Yu , Haotian Jiang , Zeyu Bao , Ruoxi Yu , Qianxiao Li

Transformers have emerged as the architecture of choice for many state-of-the-art AI models, showcasing exceptional performance across a wide range of AI applications. However, the memory demands imposed by Transformers limit their ability…

Computation and Language · Computer Science 2023-11-28 Hao Liu , Matei Zaharia , Pieter Abbeel

Looped Transformers (LT) have emerged as a powerful architecture by iterating their layers multiple times before decoding the final token. However, pairing them with full attention retains quadratic complexity, making them computationally…

Machine Learning · Computer Science 2026-05-26 Chunyuan Deng , Yizhe Zhang , Rui-Jie Zhu , Yuanyuan Xu , Jiarui Liu , T. S. Eugene Ng , Hanjie Chen

The standard content-based attention mechanism typically used in sequence-to-sequence models is computationally expensive as it requires the comparison of large encoder and decoder states at each time step. In this work, we propose an…

Computation and Language · Computer Science 2017-07-04 Denny Britz , Melody Y. Guan , Minh-Thang Luong

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

As the demand for processing extended textual data grows, the ability to handle long-range dependencies and maintain computational efficiency is more critical than ever. One of the key issues for long-sequence modeling using attention-based…

Computation and Language · Computer Science 2025-05-26 Aosong Feng , Rex Ying , Leandros Tassiulas

Accommodating long sequences efficiently in autoregressive Transformers, especially within an extended context window, poses significant challenges due to the quadratic computational complexity and substantial KV memory requirements…

Computation and Language · Computer Science 2024-06-25 Chao Lou , Zixia Jia , Zilong Zheng , Kewei Tu

The self-attention mechanism, a cornerstone of Transformer-based state-of-the-art deep learning architectures, is largely heuristic-driven and fundamentally challenging to interpret. Establishing a robust theoretical foundation to explain…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Laziz U. Abdullaev , Maksim Tkachenko , Tan M. Nguyen

The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Sparse Attention (SA)…

Machine Learning · Computer Science 2026-04-10 Quantong Qiu , Zhiyi Hong , Yi Yang , Haitian Wang , Kebin Liu , Qingqing Dang , Juntao Li , Min Zhang

Transformers have shown dominant performance across a range of domains including language and vision. However, their computational cost grows quadratically with the sequence length, making their usage prohibitive for resource-constrained…

Computation and Language · Computer Science 2023-10-24 Yinghan Long , Sayeed Shafayet Chowdhury , Kaushik Roy

Mobile vision transformers (MobileViT) can achieve state-of-the-art performance across several mobile vision tasks, including classification and detection. Though these models have fewer parameters, they have high latency as compared to…

Computer Vision and Pattern Recognition · Computer Science 2022-06-07 Sachin Mehta , Mohammad Rastegari