English
Related papers

Related papers: Residual Stream Duality in Modern Transformer Arch…

200 papers

Large language models (LLMs) excel at capturing global token dependencies via self-attention but face prohibitive compute and memory costs on lengthy inputs. While sub-quadratic methods (e.g., linear attention) can reduce these costs, they…

Machine Learning · Computer Science 2025-06-18 Yeonju Ro , Zhenyu Zhang , Souvik Kundu , Zhangyang Wang , Aditya Akella

Transformer-based deep learning models have achieved state-of-the-art performance across numerous language and vision tasks. While the self-attention mechanism, a core component of transformers, has proven capable of handling complex data…

Machine Learning · Computer Science 2025-08-05 Laziz Abdullaev , Tan M. Nguyen

Most approaches for semantic segmentation use only information from color cameras to parse the scenes, yet recent advancements show that using depth data allows to further improve performances. In this work, we focus on transformer-based…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Francesco Barbato , Giulia Rizzoli , Pietro Zanuttigh

Since transformer was firstly published in 2017, several works have been proposed to optimize it. However, the major structure of transformer remains unchanged, ignoring one of its main intrinsic limitations, which is the same static value…

Machine Learning · Computer Science 2025-12-30 Xiaowei Wang

The incredible success of transformers on sequence modeling tasks can be largely attributed to the self-attention mechanism, which allows information to be transferred between different parts of a sequence. Self-attention allows…

Machine Learning · Computer Science 2024-08-14 Eshaan Nichani , Alex Damian , Jason D. Lee

Transformers based on the attention mechanism have achieved impressive success in various areas. However, the attention mechanism has a quadratic complexity, significantly impeding Transformers from dealing with numerous tokens and scaling…

Machine Learning · Computer Science 2022-06-17 Haixu Wu , Jialong Wu , Jiehui Xu , Jianmin Wang , Mingsheng Long

When some application scenarios need to use semantic segmentation technology, like automatic driving, the primary concern comes to real-time performance rather than extremely high segmentation accuracy. To achieve a good trade-off between…

Computer Vision and Pattern Recognition · Computer Science 2023-11-01 Liang Liao , Liang Wan , Mingsheng Liu , Shusheng Li

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…

Machine Learning · Computer Science 2023-03-28 Quentin Fournier , Gaétan Marceau Caron , Daniel Aloise

Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Anxhelo Diko , Danilo Avola , Marco Cascio , Luigi Cinque

This paper introduces a novel attention mechanism, called dual attention, which is both efficient and effective. The dual attention mechanism consists of two parallel components: local attention generated by Convolutional Neural Networks…

Computer Vision and Pattern Recognition · Computer Science 2023-05-25 Zhengkai Jiang , Liang Liu , Jiangning Zhang , Yabiao Wang , Mingang Chen , Chengjie Wang

While transformers have shown great potential on video recognition with their strong capability of capturing long-range dependencies, they often suffer high computational costs induced by the self-attention to the huge number of 3D tokens.…

Computer Vision and Pattern Recognition · Computer Science 2022-11-23 Yuxuan Liang , Pan Zhou , Roger Zimmermann , Shuicheng Yan

Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding. Both are interfaced with an attention…

Computation and Language · Computer Science 2018-11-02 Maha Elbayad , Laurent Besacier , Jakob Verbeek

Existing multi-scale solutions lead to a risk of just increasing the receptive field sizes while neglecting small receptive fields. Thus, it is a challenging problem to effectively construct adaptive neural networks for recognizing various…

Computer Vision and Pattern Recognition · Computer Science 2022-09-22 Qingbei Guo , Xiao-Jun Wu , Zhiquan Feng , Tianyang Xu , Cong Hu

Relational reasoning is a central component of generally intelligent systems, enabling robust and data-efficient inductive generalization. Recent empirical evidence shows that many existing neural architectures, including Transformers,…

Machine Learning · Computer Science 2025-06-23 Awni Altabaa , John Lafferty

Transformer-based models have dramatically increased their size and parameter count to tackle increasingly complex tasks. At the same time, there is a growing demand for high performance, low-latency inference on devices with limited…

Machine Learning · Computer Science 2026-04-01 Ginés Carreto Picón , Peng Yuan Zhou , Qi Zhang , Alexandros Iosifidis

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

Time series forecasting is widely used in the fields of equipment life cycle forecasting, weather forecasting, traffic flow forecasting, and other fields. Recently, some scholars have tried to apply Transformer to time series forecasting…

Machine Learning · Computer Science 2022-02-24 Benhan Li , Shengdong Du , Tianrui Li

Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches…

Machine Learning · Computer Science 2020-10-27 Aurko Roy , Mohammad Saffar , Ashish Vaswani , David Grangier

Recently deep neural networks have been successfully applied in channel coding to improve the decoding performance. However, the state-of-the-art neural channel decoders cannot achieve high decoding performance and low complexity…

Machine Learning · Computer Science 2021-02-16 Siyu Liao , Chunhua Deng , Miao Yin , Bo Yuan

Transformers have emerged as viable alternatives to convolutional neural networks owing to their ability to learn non-local region relationships in the spatial domain. The self-attention mechanism of the transformer enables transformers to…

Image and Video Processing · Electrical Eng. & Systems 2023-08-09 Rahul G. S. , Sriprabha Ramnarayanan , Mohammad Al Fahim , Keerthi Ram , Preejith S. P , Mohanasankar Sivaprakasam