English
Related papers

Related papers: Theory, Analysis, and Best Practices for Sigmoid S…

200 papers

An attention matrix of a transformer self-attention sublayer can provably be decomposed into two components and only one of them (effective attention) contributes to the model output. This leads us to ask whether visualizing effective…

Computation and Language · Computer Science 2021-05-20 Kaiser Sun , Ana Marasović

The self-attention mechanism distinguishes transformer-based large language models (LLMs) apart from convolutional and recurrent neural networks. Despite the performance improvement, achieving real-time LLM inference on silicon remains…

Hardware Architecture · Computer Science 2024-11-18 Shiwei Liu , Guanchen Tao , Yifei Zou , Derek Chow , Zichen Fan , Kauna Lei , Bangfei Pan , Dennis Sylvester , Gregory Kielian , Mehdi Saligane

Attention is an effective mechanism to improve the deep model capability. Squeeze-and-Excite (SE) introduces a light-weight attention branch to enhance the network's representational power. The attention branch is gated using the Sigmoid…

Computer Vision and Pattern Recognition · Computer Science 2021-03-25 Chunjie Luo , Jianfeng Zhan , Tianshu Hao , Lei Wang , Wanling Gao

Following the success of dot-product attention in Transformers, numerous approximations have been recently proposed to address its quadratic complexity with respect to the input length. While these variants are memory and compute efficient,…

Computation and Language · Computer Science 2021-06-15 Ankit Gupta , Guy Dar , Shaya Goodman , David Ciprut , Jonathan Berant

The efficiency of attention is critical because its time complexity grows quadratically with sequence length. SageAttention2 addresses this by utilizing quantization to accelerate matrix multiplications (Matmul) in attention. To further…

Machine Learning · Computer Science 2025-06-09 Jintao Zhang , Xiaoming Xu , Jia Wei , Haofeng Huang , Pengle Zhang , Chendong Xiang , Jun Zhu , Jianfei Chen

Transformer networks have emerged as the state-of-the-art approach for natural language processing tasks and are gaining popularity in other domains such as computer vision and audio processing. However, the efficient hardware acceleration…

Hardware Architecture · Computer Science 2024-07-29 Gamze İslamoğlu , Moritz Scherer , Gianna Paulin , Tim Fischer , Victor J. B. Jung , Angelo Garofalo , Luca Benini

Transformer has become the dominant architecture for sequence modeling, yet a detailed understanding of how its structural parameters influence expressive power remains limited. In this work, we study the approximation properties of…

Machine Learning · Computer Science 2026-04-01 Penghao Yu , Haotian Jiang , Zeyu Bao , Ruoxi Yu , Qianxiao Li

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

Transformer-based models have brought a radical change to neural machine translation. A key feature of the Transformer architecture is the so-called multi-head attention mechanism, which allows the model to focus simultaneously on different…

Computation and Language · Computer Science 2020-10-06 Alessandro Raganato , Yves Scherrer , Jörg Tiedemann

Transformer networks, driven by self-attention, are central to Large Language Models. In generative Transformers, self-attention uses cache memory to store token projections, avoiding recomputation at each time step. However, GPU-stored…

Neural and Evolutionary Computing · Computer Science 2024-11-26 Nathan Leroux , Paul-Philipp Manea , Chirag Sudarshan , Jan Finkbeiner , Sebastian Siegel , John Paul Strachan , Emre Neftci

Transformer-based deep learning models are increasingly deployed on energy, and DRAM bandwidth constrained devices such as laptops and gaming consoles, which presents significant challenges in meeting the latency requirements of the models.…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-08-26 Aadesh Deshmukh , Venkata Yaswanth Raparti , Samuel Hsu

Multimodal Transformers serve as the backbone for state-of-the-art vision-language models, yet their quadratic attention complexity remains a critical barrier to scalability. In this work, we investigate the viability of Linear Attention…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Armin Gerami , Seyedehanita Madani , Ramani Duraiswami

Transformers have transformed the field of natural language processing. This performance is largely attributed to the use of stacked self-attention layers, each of which consists of matrix multiplies as well as softmax operations. As a…

Hardware Architecture · Computer Science 2021-03-18 Jacob R. Stevens , Rangharajan Venkatesan , Steve Dai , Brucek Khailany , Anand Raghunathan

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

Despite powering modern AI, transformers remain mysteriously brittle to train. We develop a stability theory that explains why pre-LayerNorm works, why DeepNorm uses $N^{-1/4}$ scaling, and why warmup is necessary, all from first…

Machine Learning · Computer Science 2026-02-24 Seyed Morteza Emadi

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

Transformers have demonstrated a competitive performance across a wide range of vision tasks, while it is very expensive to compute the global self-attention. Many methods limit the range of attention within a local window to reduce…

Computer Vision and Pattern Recognition · Computer Science 2022-11-01 Zhenzhe Hechen , Wei Huang , Yixin Zhao

Understanding the expressive power of transformers has recently attracted attention, as it offers insights into their abilities and limitations. Many studies analyze unique hard attention transformers, where attention selects a single…

Machine Learning · Computer Science 2025-11-14 Selim Jerad , Anej Svete , Jiaoda Li , Ryan Cotterell

We propose a novel attention mechanism, named Cog Attention, that enables attention weights to be negative for enhanced expressiveness, which stems from two key factors: (1) Cog Attention enhances parameter flexibility. For example, unlike…

Computation and Language · Computer Science 2025-01-31 Ang Lv , Ruobing Xie , Shuaipeng Li , Jiayi Liao , Xingwu Sun , Zhanhui Kang , Di Wang , Rui Yan

Sparse Attention is a technique that approximates standard attention computation with sub-quadratic complexity. This is achieved by selectively ignoring smaller entries in the attention matrix during the softmax function computation.…

Machine Learning · Computer Science 2025-02-13 Yichuan Deng , Zhao Song , Jing Xiong , Chiwun Yang