English
Related papers

Related papers: Superlinear Multi-Step Attention

200 papers

Optical coherence tomography (OCT) is one of the non-invasive and easy-to-acquire biomarkers (the thickness of the retinal layers, which is detectable within OCT scans) being investigated to diagnose Alzheimer's disease (AD). This work aims…

Image and Video Processing · Electrical Eng. & Systems 2022-06-14 Paria Jeihouni , Omid Dehzangi , Annahita Amireskandari , Ali Dabouei , Ali Rezai , Nasser M. Nasrabadi

Network reconstruction consists in determining the unobserved pairwise couplings between $N$ nodes given only observational data on the resulting behavior that is conditioned on those couplings -- typically a time-series or independent…

Data Structures and Algorithms · Computer Science 2024-05-08 Tiago P. Peixoto

Language models struggle to generalize beyond pretraining context lengths, limiting long-horizon reasoning and retrieval. Continued pretraining on long-context data can help but is expensive due to the quadratic scaling of Attention. We…

Computation and Language · Computer Science 2026-03-19 Sakshi Choudhary , Aditya Chattopadhyay , Luca Zancato , Elvis Nunez , Matthew Trager , Wei Xia , Stefano Soatto

Over the past few years, self-attention is shining in the field of deep learning, especially in the domain of natural language processing(NLP). Its impressive effectiveness, along with ubiquitous implementations, have aroused our interest…

Machine Learning · Computer Science 2020-12-03 Mingfei Yu , Masahiro Fujita

Transformer architectures deliver state-of-the-art accuracy via dense full-attention, but their quadratic time and memory complexity with respect to sequence length limits practical deployment. Linear attention mechanisms offer linear or…

Machine Learning · Computer Science 2026-01-21 Xiaojie Xia , Huigang Zhang , Chaoliang Zhong , Jun Sun , Yusuke Oishi

Attention layers -- which map a sequence of inputs to a sequence of outputs -- are core building blocks of the Transformer architecture which has achieved significant breakthroughs in modern artificial intelligence. This paper presents a…

Machine Learning · Computer Science 2023-07-24 Hengyu Fu , Tianyu Guo , Yu Bai , Song Mei

Multimodal large language models (MLLMs) recently showed strong capacity in integrating data among multiple modalities, empowered by a generalizable attention architecture. Advanced methods predominantly focus on language-centric tuning…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Zhicheng Zhang , Wuyou Xia , Chenxi Zhao , Zhou Yan , Xiaoqiang Liu , Yongjie Zhu , Wenyu Qin , Pengfei Wan , Di Zhang , Jufeng Yang

Attention has become the core building block of modern machine learning (ML) by efficiently capturing the long-range dependencies among input tokens. Its inherently parallelizable structure allows for efficient performance scaling with the…

Machine Learning · Statistics 2026-02-27 Zhenyu Liao , Jiaqing Liu , TianQi Hou , Difan Zou , Zenan Ling

Visual attention mechanisms have proven to be integrally important constituent components of many modern deep neural architectures. They provide an efficient and effective way to utilize visual information selectively, which has shown to be…

Computer Vision and Pattern Recognition · Computer Science 2019-05-24 Siddhesh Khandelwal , Leonid Sigal

Multi-head, key-value attention is the backbone of the widely successful Transformer model and its variants. This attention mechanism uses multiple parallel key-value attention blocks (called heads), each performing two fundamental…

Machine Learning · Computer Science 2022-02-15 Sarthak Mittal , Sharath Chandra Raparthy , Irina Rish , Yoshua Bengio , Guillaume Lajoie

The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large language models efficiently. For this approach, there has been significant research into…

Computation and Language · Computer Science 2026-05-26 Spandan Pratyush

Long-term memory is a cornerstone of human intelligence. Enabling AI to process lifetime-scale information remains a long-standing pursuit in the field. Due to the constraints of full-attention architectures, the effective context length of…

Computation and Language · Computer Science 2026-04-14 Yu Chen , Runkai Chen , Sheng Yi , Xinda Zhao , Xiaohong Li , Jianjin Zhang , Jun Sun , Chuanrui Hu , Yunyun Han , Lidong Bing , Yafeng Deng , Tianqiao Chen

Transformer-based large language models (LLMs) have achieved remarkable success, yet their standard attention mechanism incurs quadratic computation and memory costs with respect to sequence length, posing a major bottleneck for…

Machine Learning · Computer Science 2025-10-22 Tao Bu , Qiangang Wang , Bowen Zeng , Hanwen Sun , Yunpeng Huang , Chun Cao , Jingwei Xu

Recurrent neural networks with differentiable attention mechanisms have had success in generative and classification tasks. We show that the classification performance of such models can be enhanced by guiding a randomly initialized model…

Machine Learning · Computer Science 2017-12-18 Jack Lindsey

Continual learning aims to provide intelligent agents capable of learning multiple tasks sequentially with neural networks. One of its main challenging, catastrophic forgetting, is caused by the neural networks non-optimal ability to learn…

Machine Learning · Computer Science 2021-01-29 Ghada Sokar , Decebal Constantin Mocanu , Mykola Pechenizkiy

Attention is the cornerstone of modern Large Language Models (LLMs). Yet its quadratic complexity hinders efficiency and scalability, especially for long-context processing. A promising approach is to leverage sparsity in attention.…

Computation and Language · Computer Science 2025-02-18 Yizhao Gao , Zhichen Zeng , Dayou Du , Shijie Cao , Peiyuan Zhou , Jiaxing Qi , Junjie Lai , Hayden Kwok-Hay So , Ting Cao , Fan Yang , Mao Yang

From natural language processing to vision, Scaled Dot Product Attention (SDPA) is the backbone of most modern deep learning applications. Unfortunately, its memory and computational requirements can be prohibitive in low-resource settings.…

Machine Learning · Computer Science 2025-02-18 Peyman Hosseini , Mehran Hosseini , Ignacio Castro , Matthew Purver

Deep learning became the method of choice in recent year for solving a wide variety of predictive analytics tasks. For sequence prediction, recurrent neural networks (RNN) are often the go-to architecture for exploiting sequential…

Machine Learning · Computer Science 2016-11-09 Kin Gwn Lore , Daniel Stoecklein , Michael Davies , Baskar Ganapathysubramanian , Soumik Sarkar

Despite the recent popularity of attention-based neural architectures in core AI fields like natural language processing (NLP) and computer vision (CV), their potential in modeling complex physical systems remains under-explored. Learning…

Machine Learning · Computer Science 2024-08-15 Yue Yu , Ning Liu , Fei Lu , Tian Gao , Siavash Jafarzadeh , Stewart Silling

Even though convolutional neural networks (CNNs) are driving progress in medical image segmentation, standard models still have some drawbacks. First, the use of multi-scale approaches, i.e., encoder-decoder architectures, leads to a…

Computer Vision and Pattern Recognition · Computer Science 2020-02-18 Ashish Sinha , Jose Dolz
‹ Prev 1 8 9 10 Next ›