English
Related papers

Related papers: Myosotis: structured computation for attention lik…

200 papers

Linear-attention models that compress the entire input sequence into a fixed-size recurrent state offer an efficient alternative to Transformers, but their finite memory induces forgetfulness that harms retrieval-intensive tasks. To…

Computation and Language · Computer Science 2025-10-27 Mutian He , Philip N. Garner

One of the key challenges in machine learning is to design a computationally efficient multi-class classifier while maintaining the output accuracy and performance. In this paper, we present a tree-based classifier: Attention Tree (ATree)…

Computer Vision and Pattern Recognition · Computer Science 2016-08-03 Priyadarshini Panda , Kaushik Roy

We argue that neither transformers nor sub-quadratic architectures are well suited to training at long sequence lengths: the cost of processing the context is too expensive in the former, too inexpensive in the latter. Approaches such as…

Machine Learning · Computer Science 2025-07-08 Carles Gelada , Jacob Buckman , Sean Zhang , Txus Bach

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

Transformer models have achieved state-of-the-art results across a diverse range of domains. However, concern over the cost of training the attention mechanism to learn complex dependencies between distant inputs continues to grow. In…

While CNNs naturally lend themselves to densely sampled data, and sophisticated implementations are available, they lack the ability to efficiently process sparse data. In this work we introduce a suite of tools that exploit sparsity in…

Computer Vision and Pattern Recognition · Computer Science 2020-03-13 Timo Hackel , Mikhail Usvyatsov , Silvano Galliani , Jan D. Wegner , Konrad Schindler

Although Transformers-based architectures excel at processing textual information, their naive adaptation for tabular data often involves flattening the table structure. This simplification can lead to the loss of essential…

Computation and Language · Computer Science 2025-03-04 Raphaël Mouravieff , Benjamin Piwowarski , Sylvain Lamprier

The landscape of computational building blocks of efficient image restoration architectures is dominated by a combination of convolutional processing and various attention mechanisms. However, convolutional filters, while efficient, are…

Image and Video Processing · Electrical Eng. & Systems 2025-01-23 Mohammad Shahab Sepehri , Zalan Fabian , Mahdi Soltanolkotabi

Self-attention serves as the core foundation of large-scale transformer pretraining, but its quadratic token interaction cost makes inference expensive. Replacing attention with simpler sequential modules is appealing, yet naive…

Machine Learning · Computer Science 2026-05-20 Yuxin Ren , Maxwell D Collins , Miao Hu , Huanrui Yang

The core component of attention is the scoring function, which transforms the inputs into low-dimensional queries and keys and takes the dot product of each pair. While the low-dimensional projection improves efficiency, it causes…

Machine Learning · Computer Science 2025-09-10 Yilun Kuang , Noah Amsel , Sanae Lotfi , Shikai Qiu , Andres Potapczynski , Andrew Gordon Wilson

Long short-term memory (LSTM) is a robust recurrent neural network architecture for learning spatiotemporal sequential data. However, it requires significant computational power for learning and implementing from both software and hardware…

Machine Learning · Computer Science 2022-10-26 Nelly Elsayed , Zag ElSayed , Anthony S. Maida

Transformer-based multi-modal intelligent systems often suffer from high computational and energy costs due to dense self-attention, limiting their scalability under resource constraints. This paper presents SMMT, a sparse multi-modal…

Artificial Intelligence · Computer Science 2025-12-17 Cheng-Han Lu , Pei-Hsuan Tsai

In multi-task learning (MTL) for visual scene understanding, it is crucial to transfer useful information between multiple tasks with minimal interferences. In this paper, we propose a novel architecture that effectively transfers…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Sunkyung Kim , Hyesong Choi , Dongbo Min

Local features at neighboring spatial positions in feature maps have high correlation since their receptive fields are often overlapped. Self-attention usually uses the weighted sum (or other functions) with internal elements of each local…

Computer Vision and Pattern Recognition · Computer Science 2018-08-06 Yang Du , Chunfeng Yuan , Bing Li , Lili Zhao , Yangxi Li , Weiming Hu

Many transformations in deep learning architectures are sparsely connected. When such transformations cannot be designed by hand, they can be learned, even through plain backpropagation, for instance in attention mechanisms. However, during…

Machine Learning · Statistics 2018-10-23 Peter Bloem

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

Attention mechanisms have been extensively employed in various applications, including time series modeling, owing to their capacity to capture intricate dependencies; however, their utility is often constrained by quadratic computational…

Machine Learning · Computer Science 2025-11-06 Mingtao Zhang , Guoli Yang , Zhanxing Zhu , Mengzhu Wang , Xiaoying Bai

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Wayner Barrios , SouYoung Jin

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 aim of this work is to introduce simplicial attention networks (SANs), i.e., novel neural architectures that operate on data defined on simplicial complexes leveraging masked self-attentional layers. Hinging on formal arguments from…

Machine Learning · Computer Science 2022-03-29 L. Giusti , C. Battiloro , P. Di Lorenzo , S. Sardellitti , S. Barbarossa