English
Related papers

Related papers: ESPFormer: Doubly-Stochastic Attention with Expect…

200 papers

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

Training causal transformers at extreme sequence lengths is bottlenecked by the quadratic time and memory of scaled dot-product attention (SDPA). In this work, we propose Lighthouse Attention, a training-only symmetrical selection-based…

Computation and Language · Computer Science 2026-05-08 Bowen Peng , Subho Ghosh , Jeffrey Quesnelle

Transformer has shown great successes in natural language processing, computer vision, and audio processing. As one of its core components, the softmax attention helps to capture long-range dependencies yet prohibits its scale-up due to the…

Computation and Language · Computer Science 2022-02-18 Zhen Qin , Weixuan Sun , Hui Deng , Dongxu Li , Yunshen Wei , Baohong Lv , Junjie Yan , Lingpeng Kong , Yiran Zhong

Transformer-based language models have found many diverse applications requiring them to process sequences of increasing length. For these applications, the causal self-attention -- which is the only component scaling quadratically w.r.t.…

Machine Learning · Computer Science 2023-06-05 Matteo Pagliardini , Daniele Paliotta , Martin Jaggi , François Fleuret

Transformer attention is typically implemented using softmax normalization, which enforces attention weights with unit sum normalization. While effective in many settings, this constraint can limit flexibility in controlling attention…

Computation and Language · Computer Science 2026-02-27 Jeongin Bae , Baeseong Park , Gunho Park , Minsub Kim , Joonhyung Lee , Junhee Yoo , Sunghyeon Woo , Jiwon Ryu , Se Jung Kwon , Dongsoo Lee

Linearization of attention using various kernel approximation and kernel learning techniques has shown promise. Past methods used a subset of combinations of component functions and weight matrices within the random feature paradigm. We…

Machine Learning · Computer Science 2025-09-24 Duke Nguyen , Du Yin , Aditya Joshi , Flora Salim

Training stability is of great importance to Transformers. In this work, we investigate the training dynamics of Transformers by examining the evolution of the attention layers. In particular, we track the attention entropy for each…

Variants dropout methods have been designed for the fully-connected layer, convolutional layer and recurrent layer in neural networks, and shown to be effective to avoid overfitting. As an appealing alternative to recurrent and…

Computation and Language · Computer Science 2019-07-29 Lin Zehui , Pengfei Liu , Luyao Huang , Junkun Chen , Xipeng Qiu , Xuanjing Huang

Deep neural networks, especially transformer-based architectures, have achieved remarkable success in semantic segmentation for environmental perception. However, existing models process video frames independently, thus failing to leverage…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Serin Varghese , Kevin Ross , Fabian Hueger , Kira Maag

We introduce $\Sigma$-Attention, a Transformer-based operator-learning framework to address a key computational challenge in correlated materials. Our approach utilizes an Encoder-Only Transformer as an ansatz to approximate the self-energy…

Strongly Correlated Electrons · Physics 2025-06-02 Yuanran Zhu , Peter Rosenberg , Zhen Huang , Hardeep Bassi , Chao Yang , Shiwei Zhang

Despite the Transformer's dominance across machine learning, its architecture remains largely heuristic and lacks a unified theoretical foundation. We introduce Score-based Variational Flow (SVFlow), a continuous-time dynamical system for…

Machine Learning · Computer Science 2026-04-28 Huadong Liao

Diffusion transformers have achieved remarkable success in high-quality video generation, yet their reliance on spatiotemporal 3D full attention incurs prohibitive computational cost due to the quadratic complexity of attention. Block…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Jie Hu , Zixiang Gao , Yutong He , Kun Yuan

The state-of-the-art speech enhancement has limited performance in speech estimation accuracy. Recently, in deep learning, the Transformer shows the potential to exploit the long-range dependency in speech by self-attention. Therefore, it…

Sound · Computer Science 2023-05-10 Yi Li , Yang Sun , Syed Mohsen Naqvi

Entity tracking requires maintaining and updating latent states for entities and attributes over long sequences. Recent task-specific attention operators can compress deep Transformer stacks into a few layers by performing multi-hop state…

Machine Learning · Computer Science 2026-05-22 Hangyue Zhao , Paul Caillon , Erwan Fagnou , Alexandre Allauzen

As one of the most popular neural network modules, Transformer plays a central role in many fundamental deep learning models, e.g., the ViT in computer vision and the BERT and GPT in natural language processing. The effectiveness of the…

Machine Learning · Computer Science 2023-10-30 Shen Yuan , Hongteng Xu

We consider two biologically plausible structures, the Spiking Neural Network (SNN) and the self-attention mechanism. The former offers an energy-efficient and event-driven paradigm for deep learning, while the latter has the ability to…

Neural and Evolutionary Computing · Computer Science 2022-11-23 Zhaokun Zhou , Yuesheng Zhu , Chao He , Yaowei Wang , Shuicheng Yan , Yonghong Tian , Li Yuan

In this paper, we apply the self-attention from the state-of-the-art Transformer in Attention Is All You Need for the first time to a data-driven operator learning problem related to partial differential equations. An effort is put together…

Machine Learning · Computer Science 2021-11-02 Shuhao Cao

Route planning is essential to mobile robot navigation problems. In recent years, deep reinforcement learning (DRL) has been applied to learning optimal planning policies in stochastic environments without prior knowledge. However, existing…

Robotics · Computer Science 2023-04-21 Xi Lin , Paul Szenher , John D. Martin , Brendan Englot

Entropy estimation is essential for the performance of learned image compression. It has been demonstrated that a transformer-based entropy model is of critical importance for achieving a high compression ratio, however, at the expense of a…

Image and Video Processing · Electrical Eng. & Systems 2024-02-28 A. Burakhan Koyuncu , Panqi Jia , Atanas Boev , Elena Alshina , Eckehard Steinbach

The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly learned internal language model in the autoregressive…

Machine Learning · Computer Science 2022-09-21 Timo Lohrenz , Björn Möller , Zhengyang Li , Tim Fingscheidt