English
Related papers

Related papers: Is Attention Better Than Matrix Decomposition?

200 papers

While self-attention mechanism has shown promising results for many vision tasks, it only considers the current features at a time. We show that such a manner cannot take full advantage of the attention mechanism. In this paper, we present…

Computer Vision and Pattern Recognition · Computer Science 2020-07-13 Xu Ma , Jingda Guo , Sihai Tang , Zhinan Qiao , Qi Chen , Qing Yang , Song Fu

Memory units have been widely used to enrich the capabilities of deep networks on capturing long-term dependencies in reasoning and prediction tasks, but little investigation exists on deep generative models (DGMs) which are good at…

Machine Learning · Computer Science 2016-05-31 Chongxuan Li , Jun Zhu , Bo Zhang

Transformer-based architectures have become the prevailing backbone of large language models. However, the quadratic time and memory complexity of self-attention remains a fundamental obstacle to efficient long-context modeling. To address…

Computation and Language · Computer Science 2026-02-10 Yutao Sun , Zhenyu Li , Yike Zhang , Tengyu Pan , Bowen Dong , Yuyi Guo , Jianyong Wang

When humans describe a visual scene, they do not process the entire image uniformly; instead, they selectively fixate on regions relevant to their intended description. In contrast, current multimodal large language models (MLLMs) attend to…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Junha Song , Byeongho Heo , Geonmo Gu , Jaegul Choo , Dongyoon Han , Sangdoo Yun

Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks. However, the quadratic complexity of softmax attention remains a central bottleneck that limits their scalability. Alman and Song (NeurIPS…

Machine Learning · Computer Science 2026-03-20 Maryam Aliakbarpour , Vladimir Braverman , Junze Yin , Haochen Zhang

The attention mechanism is one of the most important priori knowledge to enhance convolutional neural networks. Most attention mechanisms are bound to the convolutional layer and use local or global contextual information to recalibrate the…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Yu Xue , Ziming Yuan

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

Intelligence necessitates memory. Without memory, humans fail to perform various nontrivial tasks such as reading novels, playing games or solving maths. As the ultimate goal of machine learning is to derive intelligent systems that learn…

Machine Learning · Computer Science 2021-07-06 Hung Le

The entropy of the codes usually serves as the rate loss in the recent learned lossy image compression methods. Precise estimation of the probabilistic distribution of the codes plays a vital role in the performance. However, existing deep…

Image and Video Processing · Electrical Eng. & Systems 2020-05-12 Mu Li , Kai Zhang , Wangmeng Zuo , Radu Timofte , David Zhang

Efficient attentions have greatly improved the computational efficiency of Transformers. However, most existing linear attention mechanisms suffer from an \emph{efficiency degradation} problem, leading to inefficiencies in causal language…

Computation and Language · Computer Science 2023-12-19 Jun Zhang , Shuyang Jiang , Jiangtao Feng , Lin Zheng , Lingpeng Kong

Models such as VGGT and $\pi^3$ have shown strong multi-view 3D performance, but their heavy reliance on global self-attention results in high computational cost. Existing sparse-attention variants offer partial speedups, yet lack a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Xianbing Sun , Zhikai Zhu , Zhengyu Lou , Bo Yang , Jinyang Tang , Liqing Zhang , He Wang , Jianfu Zhang

Transformer-based Large Language Models (LLMs) have exhibited remarkable success in extensive tasks primarily attributed to self-attention mechanism, which requires a token to consider all preceding tokens as its context to compute…

Computation and Language · Computer Science 2025-08-05 Yaofo Chen , Zeng You , Shuhai Zhang , Haokun Li , Yirui Li , Yaowei Wang , Mingkui Tan

Transformer-based models have become ubiquitous in natural language processing thanks to their large capacity, innate parallelism and high performance. The contextualizing component of a Transformer block is the $\textit{pairwise…

Machine Learning · Computer Science 2020-06-08 Ankit Gupta , Jonathan Berant

Neural Machine Translation (NMT) can be improved by including document-level contextual information. For this purpose, we propose a hierarchical attention model to capture the context in a structured and dynamic manner. The model is…

Computation and Language · Computer Science 2018-10-02 Lesly Miculicich , Dhananjay Ram , Nikolaos Pappas , James Henderson

Attention mechanisms represent a fundamental paradigm shift in neural network architectures, enabling models to selectively focus on relevant portions of input sequences through learned weighting functions. This monograph provides a…

Machine Learning · Computer Science 2026-01-08 Hasi Hays

The success of the self-attention mechanism in classical machine learning models has inspired the development of quantum analogs aimed at reducing computational overhead. Self-attention integrates learnable query and key matrices to…

Human attention modelling has proven, in recent years, to be particularly useful not only for understanding the cognitive processes underlying visual exploration, but also for providing support to artificial intelligence models that aim to…

Computer Vision and Pattern Recognition · Computer Science 2024-04-23 Giuseppe Cartella , Marcella Cornia , Vittorio Cuculo , Alessandro D'Amelio , Dario Zanca , Giuseppe Boccignone , Rita Cucchiara

Large vision-and-language models (LVLMs) have traditionally integrated visual and textual tokens by concatenating them into a single homogeneous input for large language models (LLMs), thereby maximally preserving the pre-trained language…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Chia-Wen Kuo , Sijie Zhu , Fan Chen , Xiaohui Shen , Longyin Wen

Transformer architectures have achieved state-of-the-art results on a variety of sequence modeling tasks. However, their attention mechanism comes with a quadratic complexity in sequence lengths, making the computational overhead…

Computation and Language · Computer Science 2022-06-03 Hao Peng , Jungo Kasai , Nikolaos Pappas , Dani Yogatama , Zhaofeng Wu , Lingpeng Kong , Roy Schwartz , Noah A. Smith

In recommender systems, models mostly use a combination of embedding layers and multilayer feedforward neural networks. The high-dimensional sparse original features are downscaled in the embedding layer and then fed into the fully…

Information Retrieval · Computer Science 2022-05-19 Mohan Hasama , Jing Li