English
Related papers

Related papers: GLU Attention Improve Transformer

200 papers

Recently, linear complexity sequence modeling networks have achieved modeling capabilities similar to Vision Transformers on a variety of computer vision tasks, while using fewer FLOPs and less memory. However, their advantage in terms of…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Bencheng Liao , Xinggang Wang , Lianghui Zhu , Qian Zhang , Chang Huang

State-of-the-art results on neural machine translation often use attentional sequence-to-sequence models with some form of convolution or recursion. Vaswani et al. (2017) propose a new architecture that avoids recurrence and convolution…

Artificial Intelligence · Computer Science 2017-11-08 Karim Ahmed , Nitish Shirish Keskar , Richard Socher

Activation functions and attention mechanisms are typically treated as having different purposes and have evolved differently. However, both concepts can be formulated as a non-linear gating function. Inspired by their similarity, we…

Computer Vision and Pattern Recognition · Computer Science 2020-08-04 Yimian Dai , Stefan Oehmcke , Fabian Gieseke , Yiquan Wu , Kobus Barnard

Balancing accuracy and latency on high-resolution images is a critical challenge for lightweight models, particularly for Transformer-based architectures that often suffer from excessive latency. To address this issue, we introduce…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Junzhou Li , Manqi Zhao , Yilin Gao , Zhiheng Yu , Yin Li , Dongsheng Jiang , Li Xiao

We propose a new attention mechanism, called Global Hierarchical Attention (GHA), for 3D point cloud analysis. GHA approximates the regular global dot-product attention via a series of coarsening and interpolation operations over multiple…

Computer Vision and Pattern Recognition · Computer Science 2022-08-09 Dan Jia , Alexander Hermans , Bastian Leibe

Linear attention offers a linear-time alternative to self-attention but often struggles to capture long-range patterns. We revisit linear attention through a prediction-correction lens and show that prevalent variants can be written as a…

Machine Learning · Computer Science 2025-10-01 Xunhao Lai , Jialiang Kang , Jianqiao Lu , Tong Lin , Pengyu Zhao

Transformers have revolutionized deep learning in numerous fields, including natural language processing, computer vision, and audio processing. Their strength lies in their attention mechanism, which allows for the discovering of complex…

Machine Learning · Computer Science 2024-04-02 Uladzislau Yorsh , Martin Holeňa , Ondřej Bojar , David Herel

The success of self-attention lies in its ability to capture long-range dependencies and enhance context understanding, but it is limited by its computational complexity and challenges in handling sequential data with inherent…

Computation and Language · Computer Science 2025-05-05 Md Kowsher , Nusrat Jahan Prottasha , Chun-Nam Yu , Ozlem Ozmen Garibay , Niloofar Yousefi

Gated Linear Units (GLU) and their variants are widely adopted in modern open-source large language model architectures and consistently outperform their non-gated counterparts, yet the underlying reasons for this advantage remain unclear.…

Machine Learning · Computer Science 2026-05-26 Xingyu Lyu , Qianqian Xu , Zhiyong Yang , Peisong Wen , Qingming Huang

Many sparse attention mechanisms such as Neighborhood Attention have typically failed to consistently deliver speedup over the self attention baseline. This is largely due to the level of complexity in attention infrastructure, and the…

Transformers excel at sequence modeling but face quadratic complexity, while linear attention offers improved efficiency but often compromises recall accuracy over long contexts. In this work, we introduce Native Hybrid Attention (NHA), a…

Computation and Language · Computer Science 2026-04-16 Jusen Du , Jiaxi Hu , Tao Zhang , Weigao Sun , Yu Cheng

A variety of attention mechanisms have been studied to improve the performance of various computer vision tasks. However, the prior methods overlooked the significance of retaining the information on both channel and spatial aspects to…

Computer Vision and Pattern Recognition · Computer Science 2021-12-13 Yichao Liu , Zongru Shao , Nico Hoffmann

To help address the growing demand for ever-longer sequence lengths in transformer models, Liu et al. recently proposed Ring Attention, an exact attention algorithm capable of overcoming per-device memory bottle- necks by distributing…

Machine Learning · Computer Science 2023-11-17 William Brandon , Aniruddha Nrusimha , Kevin Qian , Zachary Ankner , Tian Jin , Zhiye Song , Jonathan Ragan-Kelley

Medical image segmentation requires models that preserve fine anatomical boundaries while remaining practical for clinical deployment. Transformers capture long-range dependencies but incur quadratic attention cost, whereas CNNs are…

Computer Vision and Pattern Recognition · Computer Science 2026-05-04 Hongbo Zheng , Afshin Bozorgpour , Dorit Merhof , Minjia Zhang

Modern autoregressive models rely on attention, yet the Softmax full attention in Transformers scales quadratically with sequence length. Sliding Window Attention (SWA) achieves linear-time encoding/decoding by constraining the attention…

Machine Learning · Computer Science 2026-01-08 Jiaxu Liu , Yuhe Bai , Xiangyu Yin , Christos-Savvas Bouganis

The Transformer is a sequence model that forgoes traditional recurrent architectures in favor of a fully attention-based approach. Besides improving performance, an advantage of using attention is that it can also help to interpret a model…

Human-Computer Interaction · Computer Science 2019-06-14 Jesse Vig

Linear RNNs with gating recently demonstrated competitive performance compared to Transformers in language modeling. Although their linear compute scaling in sequence length offers theoretical runtime advantages over Transformers, realizing…

Machine Learning · Computer Science 2025-12-30 Maximilian Beck , Korbinian Pöppel , Phillip Lippe , Sepp Hochreiter

In this work we propose an energy functional along the lines of Modern Hopfield Networks (MNH), the stationary points of which correspond to the attention due to Vaswani et al. [12], thus unifying both frameworks. The minima of this…

Machine Learning · Statistics 2025-06-16 Ahmed Farooq

Transformers have been proven a successful model for a variety of tasks in sequence modeling. However, computing the attention matrix, which is their key component, has quadratic complexity with respect to the sequence length, thus making…

Machine Learning · Computer Science 2020-10-01 Apoorv Vyas , Angelos Katharopoulos , François Fleuret

Spoken Language Understanding (SLU), including intent detection and slot filling, is a core component in human-computer interaction. The natural attributes of the relationship among the two subtasks make higher requirements on fine-grained…

Computation and Language · Computer Science 2021-08-27 Dongsheng Chen , Zhiqi Huang , Yuexian Zou