English
Related papers

Related papers: Fine- and Coarse-Granularity Hybrid Self-Attention…

200 papers

Transformer-based pre-training models like BERT have achieved remarkable performance in many natural language processing tasks.However, these models are both computation and memory expensive, hindering their deployment to…

Computation and Language · Computer Science 2020-10-13 Wei Zhang , Lu Hou , Yichun Yin , Lifeng Shang , Xiao Chen , Xin Jiang , Qun Liu

We present the first unified study of the efficiency of self-attention-based Transformer variants spanning text, speech and vision. We identify input length thresholds (tipping points) at which efficient Transformer variants become more…

Computation and Language · Computer Science 2023-06-16 Anuj Diwan , Eunsol Choi , David Harwath

The self-attention mechanism, while foundational to modern Transformer architectures, suffers from a critical inefficiency: it frequently allocates substantial attention to redundant or noisy context. Differential Attention addressed this…

In long-context large language model (LLM) inference, the prefill stage dominates computation due to self-attention over the complete input context. Sparse attention significantly reduces self-attention computation by limiting each token's…

Hardware Architecture · Computer Science 2026-02-25 Rakshith Jayanth , Viktor Prasanna

The remarkable success of transformers in sequence modeling tasks, spanning various applications in natural language processing and computer vision, is attributed to the critical role of self-attention. Similar to the development of most…

Machine Learning · Computer Science 2024-11-01 Rachel S. Y. Teo , Tan M. Nguyen

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

We study efficient reasoning under tight compute. We ask how to make structured, correct decisions without increasing test time cost. We add two training only components to small and medium Transformers that also transfer to broader…

Machine Learning · Computer Science 2026-03-11 Rian Atri

Attention serves as the fundamental mechanism for long-context modeling in large language models (LLMs), yet dense attention becomes structurally prohibitive for long sequences due to its quadratic complexity. Consequently, sparse attention…

Computation and Language · Computer Science 2026-01-07 Junxiang Qiu , Shuo Wang , Zhengsu Chen , Hengheng Zhang , Jinda Lu , Changcheng Li , Qi Tian

The core for tackling the fine-grained visual categorization (FGVC) is to learn subtle yet discriminative features. Most previous works achieve this by explicitly selecting the discriminative parts or integrating the attention mechanism via…

Computer Vision and Pattern Recognition · Computer Science 2022-03-02 Jun Wang , Xiaohan Yu , Yongsheng Gao

Federated learning (FL) is a promising distributed paradigm, eliminating the need for data sharing but facing challenges from data heterogeneity. Personalized parameter generation through a hypernetwork proves effective, yet existing…

Computer Vision and Pattern Recognition · Computer Science 2023-11-22 Ziyuan Yang , Zerui Shao , Huijie Huangfu , Hui Yu , Andrew Beng Jin Teoh , Xiaoxiao Li , Hongming Shan , Yi Zhang

Transformer models rely heavily on the scaled dot-product attention (SDPA) operation, typically implemented as FlashAttention. Characterized by its frequent interleaving of matrix multiplications and softmax operations, FlashAttention fails…

Hardware Architecture · Computer Science 2025-12-09 Jiawei Lin , Yuanlong Li , Guokai Chen , Thomas Bourgeat

The Transformer architecture, underpinned by the Multi-Head Attention (MHA) mechanism, has become the de facto standard for state-of-the-art models in artificial intelligence. However, the quadratic computational complexity of MHA with…

Machine Learning · Computer Science 2025-10-03 Adam Filipek

In this paper, we aim to improve the robustness of Keyword Spotting (KWS) systems in noisy environments while keeping a small memory footprint. We propose a new convolutional neural network (CNN) called FCA-Net, which combines mixer…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-30 Yuanxi Lin , Yuriy Evgenyevich Gapanyuk

Random-feature-based attention (RFA) is an efficient approximation of softmax attention with linear runtime and space complexity. However, the approximation gap between RFA and conventional softmax attention is not well studied. Built upon…

Machine Learning · Computer Science 2023-02-10 Lin Zheng , Jianbo Yuan , Chong Wang , Lingpeng Kong

In this work, we investigate several neural network architectures for fine-grained entity type classification. Particularly, we consider extensions to a recently proposed attentive neural architecture and make three key contributions.…

Computation and Language · Computer Science 2017-02-22 Sonse Shimaoka , Pontus Stenetorp , Kentaro Inui , Sebastian Riedel

The favorable performance of Vision Transformers (ViTs) is often attributed to the multi-head self-attention (MSA). The MSA enables global interactions at each layer of a ViT model, which is a contrasting feature against Convolutional…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Nam Hyeon-Woo , Kim Yu-Ji , Byeongho Heo , Dongyoon Han , Seong Joon Oh , Tae-Hyun Oh

Long-context transformers face significant efficiency challenges due to the quadratic cost of self-attention. However, many modern applications-from multi-turn dialogue to high-resolution vision-require contexts spanning tens of thousands…

Machine Learning · Computer Science 2025-05-20 Jacob Fein-Ashley , Neelesh Gupta , Rajgopal Kannan , Viktor Prasanna

Pre-trained language models achieve superior performance but are computationally expensive. Techniques such as pruning and knowledge distillation have been developed to reduce their sizes and latencies. In this work, we propose a structured…

Computation and Language · Computer Science 2023-05-19 Ziqing Yang , Yiming Cui , Xin Yao , Shijin Wang

Attention-based large language models (LLMs) have transformed modern AI applications, but the quadratic cost of self-attention imposes significant compute and memory overhead. Dynamic sparsity (DS) attention mitigates this, yet its hardware…

Machine Learning · Computer Science 2025-12-09 Huizheng Wang , Hongbin Wang , Shaojun Wei , Yang Hu , Shouyi Yin

Pre-trained contextual representations (e.g., BERT) have become the foundation to achieve state-of-the-art results on many NLP tasks. However, large-scale pre-training is computationally expensive. ELECTRA, an early attempt to accelerate…

Computation and Language · Computer Science 2020-06-17 Zhenhui Xu , Linyuan Gong , Guolin Ke , Di He , Shuxin Zheng , Liwei Wang , Jiang Bian , Tie-Yan Liu
‹ Prev 1 4 5 6 7 8 10 Next ›