English
Related papers

Related papers: Normalized Attention Without Probability Cage

200 papers

Transformers are built upon multi-head scaled dot-product attention and positional encoding, which aim to learn the feature representations and token dependencies. In this work, we focus on enhancing the distinctive representation by…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Litao Yu , Jian Zhang

The quadratic computational and memory complexities of the Transformer's attention mechanism have limited its scalability for modeling long sequences. In this paper, we propose Luna, a linear unified nested attention mechanism that…

Machine Learning · Computer Science 2021-11-04 Xuezhe Ma , Xiang Kong , Sinong Wang , Chunting Zhou , Jonathan May , Hao Ma , Luke Zettlemoyer

Gating mechanisms have been widely utilized, from early models like LSTMs and Highway Networks to recent state space models, linear attention, and also softmax attention. Yet, existing literature rarely examines the specific effects of…

Computation and Language · Computer Science 2025-05-13 Zihan Qiu , Zekun Wang , Bo Zheng , Zeyu Huang , Kaiyue Wen , Songlin Yang , Rui Men , Le Yu , Fei Huang , Suozhi Huang , Dayiheng Liu , Jingren Zhou , Junyang Lin

Multi-head attention enables transformer models to represent multiple attention patterns simultaneously. Empirically, head specialization emerges in distinct stages during training, while many heads remain redundant and learn similar…

Machine Learning · Computer Science 2026-03-05 M. Sagitova , O. Duranthon , L. Zdeborová

Normalization techniques are crucial for enhancing Transformer models' performance and stability in time series analysis tasks, yet traditional methods like batch and layer normalization often lead to issues such as token shift, attention…

Machine Learning · Computer Science 2024-05-28 Nan Huang , Christian Kümmerle , Xiang Zhang

The dot product self-attention is known to be central and indispensable to state-of-the-art Transformer models. But is it really required? This paper investigates the true importance and contribution of the dot product-based self-attention…

Computation and Language · Computer Science 2021-05-25 Yi Tay , Dara Bahri , Donald Metzler , Da-Cheng Juan , Zhe Zhao , Che Zheng

Various linear complexity models, such as Linear Transformer (LinFormer), State Space Model (SSM), and Linear RNN (LinRNN), have been proposed to replace the conventional softmax attention in Transformer structures. However, the optimal…

Machine Learning · Computer Science 2024-11-19 Yuhong Chou , Man Yao , Kexin Wang , Yuqi Pan , Ruijie Zhu , Yiran Zhong , Yu Qiao , Jibin Wu , Bo Xu , Guoqi Li

Transformers have dominated sequence processing tasks for the past seven years -- most notably language modeling. However, the inherent quadratic complexity of their attention mechanism remains a significant bottleneck as context length…

Computation and Language · Computer Science 2025-10-08 Alexander M. Fichtl , Jeremias Bohn , Josefin Kelber , Edoardo Mosca , Georg Groh

The Transformer architecture model, based on self-attention and multi-head attention, has achieved remarkable success in offline end-to-end Automatic Speech Recognition (ASR). However, self-attention and multi-head attention cannot be…

Computation and Language · Computer Science 2022-10-03 Chendong Zhao , Jianzong Wang , Wen qi Wei , Xiaoyang Qu , Haoqian Wang , Jing Xiao

The training and generalization dynamics of the Transformer's core mechanism, namely the Attention mechanism, remain under-explored. Besides, existing analyses primarily focus on single-head attention. Inspired by the demonstrated benefits…

Machine Learning · Computer Science 2024-10-15 Puneesh Deora , Rouzbeh Ghaderi , Hossein Taheri , Christos Thrampoulidis

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

The Transformer architecture has become a cornerstone of modern artificial intelligence, but its core self-attention mechanism suffers from a complexity bottleneck that scales quadratically with sequence length, severely limiting its…

Machine Learning · Computer Science 2025-08-29 Zhongpan Tang

Large language models have achieved remarkable success in recent years, primarily due to self-attention. However, traditional Softmax attention suffers from numerical instability and reduced performance as the number of inference tokens…

Computation and Language · Computer Science 2026-02-02 Bo Gao , Michael W. Spratling , Letizia Gionfrida

We introduce a new discrete-time attention model, termed the localmax dynamics, which interpolates between the classic softmax dynamics and the hardmax dynamics, where only the tokens that maximize the influence toward a given token have a…

Computation and Language · Computer Science 2025-09-22 Henri Cimetière , Maria Teresa Chiri , Bahman Gharesifard

The attention operator is arguably the key distinguishing factor of transformer architectures, which have demonstrated state-of-the-art performance on a variety of tasks. However, transformer attention operators often impose a significant…

Machine Learning · Computer Science 2024-12-24 Ziyang Wu , Tianjiao Ding , Yifu Lu , Druv Pai , Jingyuan Zhang , Weida Wang , Yaodong Yu , Yi Ma , Benjamin D. Haeffele

Attention modules, as simple and effective tools, have not only enabled deep neural networks to achieve state-of-the-art results in many domains, but also enhanced their interpretability. Most current models use deterministic attention…

Machine Learning · Statistics 2020-10-22 Xinjie Fan , Shujian Zhang , Bo Chen , Mingyuan Zhou

Transformers have recently revolutionized many domains in modern machine learning and one salient discovery is their remarkable in-context learning capability, where models can solve an unseen task by utilizing task-specific prompts without…

Machine Learning · Computer Science 2023-10-10 Yu Huang , Yuan Cheng , Yingbin Liang

Transformers with linear attention allow for efficient parallel training but can simultaneously be formulated as an RNN with 2D (matrix-valued) hidden states, thus enjoying linear-time inference complexity. However, linear attention…

Machine Learning · Computer Science 2024-08-28 Songlin Yang , Bailin Wang , Yikang Shen , Rameswar Panda , Yoon Kim

The attention mechanism in Transformers is an important primitive for accurate and scalable sequence modeling. Its quadratic-compute and linear-memory complexity however remain significant bottlenecks. Linear attention and state-space…

Machine Learning · Computer Science 2026-03-03 Han Guo , Songlin Yang , Tarushii Goel , Eric P. Xing , Tri Dao , Yoon Kim

Since its introduction, softmax attention has become the backbone of modern transformer architectures due to its expressiveness and scalability across a wide range of tasks. However, the main drawback of softmax attention is the quadratic…

Machine Learning · Computer Science 2026-02-20 Gabriel Mongaras , Eric C. Larson