English
Related papers

Related papers: Attention Residuals

200 papers

Tabular data streams are increasingly prevalent in real-time decision-making across healthcare, finance, and the Internet of Things, often generated and processed on resource-constrained edge and mobile devices. Continual learning (CL)…

Machine Learning · Computer Science 2026-02-06 Yuandou Wang , Filip Gunnarsson , Rihan Hai

Various architectures (such as GoogLeNets, ResNets, and DenseNets) have been proposed. However, the existing networks usually suffer from either redundancy of convolutional layers or insufficient utilization of parameters. To handle these…

Computer Vision and Pattern Recognition · Computer Science 2020-04-27 Zhiyu Zhu , Zhen-Peng Bian , Junhui Hou , Yi Wang , Lap-Pui Chau

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

Scaling the context length of large language models (LLMs) offers significant benefits but is computationally expensive. This expense stems primarily from the self-attention mechanism, whose $O(N^2)$ complexity with respect to sequence…

Computation and Language · Computer Science 2026-05-25 Xinghao Wang , Pengyu Wang , Dong Zhang , Chenkun Tan , Shaojun Zhou , Zhaoxiang Liu , Shiguo Lian , Fangxu Liu , Kai Song , Xipeng Qiu

We present Lightning Attention, the first linear attention implementation that maintains a constant training speed for various sequence lengths under fixed memory consumption. Due to the issue with cumulative summation operations (cumsum),…

Computation and Language · Computer Science 2024-06-21 Zhen Qin , Weigao Sun , Dong Li , Xuyang Shen , Weixuan Sun , Yiran Zhong

Linear attention offers a computationally efficient yet expressive alternative to softmax attention. However, recent empirical results indicate that the hidden state of trained linear attention models often exhibits a low-rank structure,…

Machine Learning · Computer Science 2026-02-13 Philipp Nazari , T. Konstantin Rusch

Key-Value (KV) cache memory and bandwidth increasingly dominate large language model inference cost in long-context and long-generation regimes. Architectures such as multi-head latent attention (MLA) and hybrid sliding-window attention…

Computation and Language · Computer Science 2026-04-08 Zhen Cheng , Hao-Bo Yang , Wan-Yi Huang , Jin-Long Li

With the growing adoption of deep learning for on-device TinyML applications, there has been an ever-increasing demand for efficient neural network backbones optimized for the edge. Recently, the introduction of attention condenser networks…

Computer Vision and Pattern Recognition · Computer Science 2023-02-06 Alexander Wong , Mohammad Javad Shafiee , Saad Abbasi , Saeejith Nair , Mahmoud Famouri

We propose the attention-inspired numerical solver (AttNS), a concise method that helps the generalization and robustness issues faced by the AI-Hybrid numerical solver in solving differential equations due to limited data. AttNS is…

Machine Learning · Computer Science 2025-02-06 Zhongzhan Huang , Mingfu Liang , Shanshan Zhong , Liang Lin

Attention-based architectures have become ubiquitous in machine learning, yet our understanding of the reasons for their effectiveness remains limited. This work proposes a new way to understand self-attention networks: we show that their…

Machine Learning · Computer Science 2023-08-02 Yihe Dong , Jean-Baptiste Cordonnier , Andreas Loukas

This paper proposes a novel Attention-based Multi-Reference Super-resolution network (AMRSR) that, given a low-resolution image, learns to adaptively transfer the most similar texture from multiple reference images to the super-resolution…

Computer Vision and Pattern Recognition · Computer Science 2021-09-01 Marco Pesavento , Marco Volino , Adrian Hilton

Convolutional neural networks are the most successful models in single image super-resolution. Deeper networks, residual connections, and attention mechanisms have further improved their performance. However, these strategies often improve…

Image and Video Processing · Electrical Eng. & Systems 2020-12-09 Parichehr Behjati , Pau Rodriguez , Armin Mehri , Isabelle Hupont , Carles Fernández Tena , Jordi Gonzalez

In contrast to RNNs, which compress their history into a single hidden state, Transformers can attend to all past tokens directly. However, standard Transformers rely solely on the hidden state from the previous layer to represent the…

Machine Learning · Computer Science 2025-05-29 Gleb Gerasimov , Yaroslav Aksenov , Nikita Balagansky , Viacheslav Sinii , Daniil Gavrilov

The performance of Large Language Models (LLMs) is significantly sensitive to the contextual position of information in the input. To investigate the mechanism behind this positional bias, our extensive experiments reveal a consistent…

Computation and Language · Computer Science 2025-08-08 Zihao Yi , Delong Zeng , Zhenqing Ling , Haohao Luo , Zhe Xu , Wei Liu , Jian Luan , Wanxia Cao , Ying Shen

In this work, we propose "Residual Attention Network", a convolutional neural network using attention mechanism which can incorporate with state-of-art feed forward network architecture in an end-to-end training fashion. Our Residual…

Computer Vision and Pattern Recognition · Computer Science 2017-04-25 Fei Wang , Mengqing Jiang , Chen Qian , Shuo Yang , Cheng Li , Honggang Zhang , Xiaogang Wang , Xiaoou Tang

We present TransNormerLLM, the first linear attention-based Large Language Model (LLM) that outperforms conventional softmax attention-based models in terms of both accuracy and efficiency. TransNormerLLM evolves from the previous linear…

Computation and Language · Computer Science 2024-01-22 Zhen Qin , Dong Li , Weigao Sun , Weixuan Sun , Xuyang Shen , Xiaodong Han , Yunshen Wei , Baohong Lv , Xiao Luo , Yu Qiao , Yiran Zhong

Efficient parallelization of Large Language Models (LLMs) with long sequences is essential but challenging due to their significant computational and memory demands, particularly stemming from communication bottlenecks in attention…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-12-31 Zongwu Wang , Fangxin Liu , Mingshuai Li , Li Jiang

Sequence models face a fundamental tradeoff between memory capacity and computational efficiency. Transformers achieve expressive context modeling at quadratic cost, while linear attention and state-space models run in linear time by…

Machine Learning · Computer Science 2026-05-11 Yaxita Amin , Helen Zichen Li , Mengfan Zhang , Samet Ayhan

Multimodal Large Language Models (MLLMs) incur significant computational cost from processing numerous vision tokens through all LLM layers. Prior pruning methods operate either before the LLM, limiting generality due to diverse…

Computer Vision and Pattern Recognition · Computer Science 2026-02-16 Omer Faruk Deniz , Ruiyu Mao , Ruochen Li , Yapeng Tian , Latifur Khan

Transformer-based Large Language Models (LLMs) have become increasingly important. However, due to the quadratic time complexity of attention computation, scaling LLMs to longer contexts incurs extremely slow inference speed and high GPU…