English
Related papers

Related papers: Differential Gated Self-Attention

200 papers

Surface meshes are a favoured domain for representing structural and functional information on the human cortex, but their complex topology and geometry pose significant challenges for deep learning analysis. While Transformers have…

Image and Video Processing · Electrical Eng. & Systems 2024-06-12 Simon Dahan , Logan Z. J. Williams , Daniel Rueckert , Emma C. Robinson

The paradigm of Transformers using the self-attention mechanism has manifested its advantage in learning graph-structured data. Yet, Graph Transformers are capable of modeling full range dependencies but are often deficient in extracting…

Machine Learning · Computer Science 2024-09-11 Minhong Zhu , Zhenhao Zhao , Weiran Cai

We propose a dual-stream multi-scale vision transformer (DS-MSHViT) architecture that processes RGB and optical flow inputs for efficient sewer defect classification. Unlike existing methods that combine the predictions of two separate…

Computer Vision and Pattern Recognition · Computer Science 2023-11-29 Abdullah Al Redwan Newaz , Mahdi Abdeldguerfi , Kendall N. Niles , Joe Tom

Diffusion Transformers (DiTs) set the state of the art in visual generation, yet their quadratic self-attention cost fundamentally limits scaling to long token sequences. Recent Top-K sparse attention approaches reduce the computation of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Yifan Zhou , Zeqi Xiao , Tianyi Wei , Shuai Yang , Xingang Pan

We propose a variational quantum implementation of self-attention (QSA), the core operation in transformers and large language models, which predicts future elements of a sequence by forming overlap-weighted combinations of past data. At…

Quantum Physics · Physics 2026-02-09 Alessio Pecilli , Matteo Rosati

We study the capacity of the self-attention key-query channel: for a fixed budget, how many distinct token-token relations can a single layer reliably encode? We introduce Relational Graph Recognition, where the key-query channel encodes a…

Machine Learning · Computer Science 2026-02-04 Micah Adler

Transformer networks have achieved remarkable success across diverse domains, leveraging a variety of architectural innovations, including residual connections. However, traditional residual connections, which simply sum the outputs of…

Machine Learning · Computer Science 2025-07-25 Mike Heddes , Adel Javanmard , Kyriakos Axiotis , Gang Fu , MohammadHossein Bateni , Vahab Mirrokni

DIFF Transformer improves attention allocation by enhancing focus on relevant context while suppressing noise. It introduces a differential attention mechanism that calculates the difference between two independently generated attention…

Machine Learning · Computer Science 2025-12-17 Yueyang Cang , Yuhang Liu , Xiaoteng Zhang , Li Shi , Wenge Que

Self-attention has been a huge success for many downstream tasks in NLP, which led to exploration of applying self-attention to speech problems as well. The efficacy of self-attention in speech applications, however, seems not fully blown…

Computation and Language · Computer Science 2019-10-03 Kyu J. Han , Ramon Prieto , Kaixing Wu , Tao Ma

Efficiently supporting long context length is crucial for Transformer models. The quadratic complexity of the self-attention computation plagues traditional Transformers. Sliding window-based static sparse attention mitigates the problem by…

Hardware Architecture · Computer Science 2024-05-28 Zhenyu Bai , Pranav Dangi , Huize Li , Tulika Mitra

The Transformer has shown impressive performance in automatic speech recognition. It uses the encoder-decoder structure with self-attention to learn the relationship between the high-level representation of the source inputs and embedding…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-16 Xinyuan Zhou , Grandee Lee , Emre Yılmaz , Yanhua Long , Jiaen Liang , Haizhou Li

Transformers have become one of the most important architectural innovations in deep learning and have enabled many breakthroughs over the past few years. Here we propose a simple network architecture, gMLP, based on MLPs with gating, and…

Machine Learning · Computer Science 2021-06-03 Hanxiao Liu , Zihang Dai , David R. So , Quoc V. Le

Hand-crafted spatial features, such as inter-channel intensity difference (IID) and inter-channel phase difference (IPD), play a fundamental role in recent deep learning based dual-microphone speech enhancement (DMSE) systems. However,…

Audio and Speech Processing · Electrical Eng. & Systems 2022-05-04 Xinmeng Xu , Rongzhi Gu , Yuexian Zou

Models based on the Transformer neural network architecture have seen success on a wide variety of tasks that appear to require complex "cognitive branching" -- or the ability to maintain pursuit of one goal while accomplishing others. In…

Artificial Intelligence · Computer Science 2024-02-14 Aaron Traylor , Jack Merullo , Michael J. Frank , Ellie Pavlick

Transformers are considered one of the most important deep learning models since 2018, in part because it establishes state-of-the-art (SOTA) records and could potentially replace existing Deep Neural Networks (DNNs). Despite the remarkable…

Machine Learning · Computer Science 2022-08-23 Hongwu Peng , Shaoyi Huang , Shiyang Chen , Bingbing Li , Tong Geng , Ang Li , Weiwen Jiang , Wujie Wen , Jinbo Bi , Hang Liu , Caiwen Ding

Despite the popularity of transformers in practice, their architectures are empirically designed and neither mathematically justified nor interpretable. Moreover, as indicated by many empirical studies, some components of transformer…

Machine Learning · Computer Science 2025-06-05 Peng Wang , Yifu Lu , Yaodong Yu , Druv Pai , Qing Qu , Yi Ma

We propose SG-XDEAT (Sparsity-Guided Cross Dimensional and Cross-Encoding Attention with Target Aware Conditioning), a novel framework designed for supervised learning on tabular data. At its core, SG-XDEAT employs a dual-stream encoder…

Machine Learning · Computer Science 2025-10-15 Chih-Chuan Cheng , Yi-Ju Tseng

At the core of the popular Transformer architecture is the self-attention mechanism, which dynamically assigns softmax weights to each input token so that the model can focus on the most salient information. However, the softmax structure…

Machine Learning · Computer Science 2025-05-27 Fanqi Yan , Huy Nguyen , Pedram Akbarian , Nhat Ho , Alessandro Rinaldo

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…

Transparent object perception remains a major challenge in computer vision research, as transparency confounds both depth estimation and semantic segmentation. Recent work has explored multi-task learning frameworks to improve robustness,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-20 Gbenga Omotara , Ramy Farag , Seyed Mohamad Ali Tousi , G. N. DeSouza