English
Related papers

Related papers: Why Softmax Attention Outperforms Linear Attention

200 papers

Differential Transformer has recently gained significant attention for its impressive empirical performance, often attributed to its ability to perform noise canceled attention. However, precisely how differential attention achieves its…

Machine Learning · Computer Science 2025-10-22 Chaerin Kong , Jiho Jang , Nojun Kwak

Transformers serve as the foundation of most modern large language models. To mitigate the quadratic complexity of standard full attention, various efficient attention mechanisms, such as linear and hybrid attention, have been developed. A…

Machine Learning · Computer Science 2026-02-03 Xiaowei Ye , Xiaoyu He , Chao Liao , Chen Wu , Pinyan Lu

Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of…

Computation and Language · Computer Science 2019-12-30 Guangxiang Zhao , Junyang Lin , Zhiyuan Zhang , Xuancheng Ren , Qi Su , Xu Sun

Transformers have become the cornerstone of modern large-scale language models, but their reliance on softmax attention poses a computational bottleneck at both training and inference. Recurrent models offer high efficiency, but compressing…

Computation and Language · Computer Science 2025-11-20 Xiuying Wei , Anunay Yadav , Razvan Pascanu , Caglar Gulcehre

While linear-complexity attention mechanisms offer a promising alternative to Softmax attention for overcoming the quadratic bottleneck, training such models from scratch remains prohibitively expensive. Inheriting weights from pretrained…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Yining Li , Dongchen Han , Zeyu Liu , Hanyi Wang , Yulin Wang , Gao Huang

This paper investigates the limitations of transformers for entity-tracking tasks in large language models. We identify a theoretical constraint, showing that transformers require at least $\log_2 (n+1)$ layers to handle entity tracking…

Machine Learning · Computer Science 2024-12-12 Erwan Fagnou , Paul Caillon , Blaise Delattre , Alexandre Allauzen

While the approximation properties of single-layer Transformer architectures have been studied in recent works, a rigorous theoretical understanding of the multi-layer setting remains limited. In this work, we establish that multi-layer…

Machine Learning · Computer Science 2026-05-19 Penghao Yu , Haotian Jiang , Zeyu Bao , Qianxiao Li

The attention mechanism is considered the backbone of the widely-used Transformer architecture. It contextualizes the input by computing input-specific attention matrices. We find that this mechanism, while powerful and elegant, is not as…

Computation and Language · Computer Science 2022-11-08 Michael Hassid , Hao Peng , Daniel Rotem , Jungo Kasai , Ivan Montero , Noah A. Smith , Roy Schwartz

The change point is a moment of an abrupt alteration in the data distribution. Current methods for change point detection are based on recurrent neural methods suitable for sequential data. However, recent works show that transformers based…

Machine Learning · Computer Science 2022-04-19 Anna Dmitrienko , Evgenia Romanenkova , Alexey Zaytsev

We describe an efficient hierarchical method to compute attention in the Transformer architecture. The proposed attention mechanism exploits a matrix structure similar to the Hierarchical Matrix (H-Matrix) developed by the numerical…

Machine Learning · Computer Science 2021-07-27 Zhenhai Zhu , Radu Soricut

Time series forecasting is essential for many practical applications, with the adoption of transformer-based models on the rise due to their impressive performance in NLP and CV. Transformers' key feature, the attention mechanism,…

Machine Learning · Computer Science 2024-02-09 PeiSong Niu , Tian Zhou , Xue Wang , Liang Sun , Rong Jin

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…

Machine Learning · Computer Science 2025-07-01 Venmugil Elango

Linear attention methods offer Transformers $O(N)$ complexity but typically underperform standard softmax attention. We identify two fundamental limitations affecting these approaches: the restriction to convex combinations that only…

Machine Learning · Computer Science 2026-02-06 Jiecheng Lu , Xu Han , Yan Sun , Viresh Pati , Yubin Kim , Siddhartha Somani , Shihao Yang

Transformer is a powerful architecture that achieves superior performance on various sequence learning tasks, including neural machine translation, language understanding, and sequence prediction. At the core of the Transformer is the…

Machine Learning · Computer Science 2019-11-13 Yao-Hung Hubert Tsai , Shaojie Bai , Makoto Yamada , Louis-Philippe Morency , Ruslan Salakhutdinov

Transformer-based models, even though achieving super-human performance on several downstream tasks, are often regarded as a black box and used as a whole. It is still unclear what mechanisms they have learned, especially their core module:…

Computation and Language · Computer Science 2023-10-17 Chong Li , Shaonan Wang , Yunhao Zhang , Jiajun Zhang , Chengqing Zong

Existing expressivity results for transformers typically rely on hardmax attention, high precision, and other architectural modifications that disconnect them from the models used in practice. We bridge this gap by analyzing standard…

Machine Learning · Computer Science 2026-05-19 Moritz Brösamle , Stephan Eckstein

Modeling long sequences of user behaviors has emerged as a critical frontier in generative recommendation. However, existing solutions face a dilemma: linear attention mechanisms achieve efficiency at the cost of retrieval precision due to…

Information Retrieval · Computer Science 2026-02-23 Lei Xin , Yuhao Zheng , Ke Cheng , Changjiang Jiang , Zifan Zhang , Fanhu Zeng

Large Language Models (LLMs), built on Transformer architectures, exhibit remarkable generalization across a wide range of tasks. However, fine-tuning these models for specific tasks remains resource-intensive due to their extensive…

Machine Learning · Computer Science 2025-05-15 Xinhao Yao , Hongjin Qian , Xiaolin Hu , Gengze Xu , Wei Liu , Jian Luan , Bin Wang , Yong Liu

Recently, self-attention models such as Transformers have given competitive results compared to recurrent neural network systems in speech recognition. The key factor for the outstanding performance of self-attention models is their ability…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-29 Shucong Zhang , Erfan Loweimi , Peter Bell , Steve Renals

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
‹ Prev 1 8 9 10 Next ›