English
Related papers

Related papers: Stable, Fast and Accurate: Kernelized Attention wi…

200 papers

Transformer-based models have achieved great success in various NLP, vision, and speech tasks. However, the core of Transformer, the self-attention mechanism, has a quadratic time and memory complexity with respect to the sequence length,…

Computation and Language · Computer Science 2023-05-23 Chao-Hong Tan , Qian Chen , Wen Wang , Qinglin Zhang , Siqi Zheng , Zhen-Hua Ling

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

In this paper, we propose a vision model that adopts token mixing, sequence-pooling, and convolutional tokenizers to achieve state-of-the-art performance and efficient inference in fixed context-length tasks. In the CIFAR100 benchmark, our…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Simpenzwe Honore Leandre , Natenaile Asmamaw Shiferaw , Dillip Rout

Benefiting from the capability of building inter-dependencies among channels or spatial locations, attention mechanisms have been extensively studied and broadly used in a variety of computer vision tasks recently. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2020-11-09 Diganta Misra , Trikay Nalamada , Ajay Uppili Arasanipalai , Qibin Hou

Transformers are considered one of the most important deep learning models since 2018, in part because it establishes state-of-the-art (SOTA) records and could potentially replace existing Deep Neural Networks (DNNs). Despite the remarkable…

Machine Learning · Computer Science 2022-08-23 Hongwu Peng , Shaoyi Huang , Shiyang Chen , Bingbing Li , Tong Geng , Ang Li , Weiwen Jiang , Wujie Wen , Jinbo Bi , Hang Liu , Caiwen Ding

Entity tracking requires maintaining and updating latent states for entities and attributes over long sequences. Recent task-specific attention operators can compress deep Transformer stacks into a few layers by performing multi-hop state…

Machine Learning · Computer Science 2026-05-22 Hangyue Zhao , Paul Caillon , Erwan Fagnou , Alexandre Allauzen

The quadratic complexity of self-attention in Transformers has hindered the processing of long text. To alleviate this problem, previous works have proposed to sparsify the attention matrix, taking advantage of the observation that crucial…

Computation and Language · Computer Science 2024-01-12 Ziwei He , Jian Yuan , Le Zhou , Jingwen Leng , Bo Jiang

Length generalization is the ability of language models to maintain performance on inputs longer than those seen during pretraining. In this work, we introduce a simple yet powerful position encoding (PE) strategy, Random Float Sampling…

Machine Learning · Computer Science 2026-02-17 Atsushi Shimizu , Shohei Taniguchi , Yutaka Matsuo

Transformers have demonstrated remarkable success across vision, language, and video. Yet, increasing task complexity has led to larger models and more tokens, raising the quadratic cost of self-attention and the overhead of GPU memory…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Joonmyung Choi , Sanghyeok Lee , Byungoh Ko , Eunseo Kim , Jihyung Kil , Hyunwoo J. Kim

Standard transformer attention computes pairwise token similarity but treats all tokens as equally salient and all positions as equally local, regardless of the informational structure of the input. We identify two complementary inductive…

Machine Learning · Computer Science 2026-05-27 Athanasios Zeris

We propose a simple modification to the conventional attention mechanism applied by Transformers: Instead of quantifying pairwise query-key similarity with scaled dot-products, we quantify it with the logarithms of scaled dot-products of…

Machine Learning · Computer Science 2024-04-30 Franz A. Heinsen

The paradigm of Transformers using the self-attention mechanism has manifested its advantage in learning graph-structured data. Yet, Graph Transformers are capable of modeling full range dependencies but are often deficient in extracting…

Machine Learning · Computer Science 2024-09-11 Minhong Zhu , Zhenhao Zhao , Weiran Cai

Despite the significant progress made by transformer models in machine reading comprehension tasks, they still fall short in handling complex reasoning tasks due to the absence of explicit knowledge in the input sequence. To address this…

Computation and Language · Computer Science 2024-01-17 Shima Foolad , Kourosh Kiani

Tensor Attention, a multi-view attention that is able to capture high-order correlations among multiple modalities, can overcome the representational limitations of classical matrix attention. However, the $O(n^3)$ time complexity of tensor…

Machine Learning · Computer Science 2026-01-27 Yang Cao , Yingyu Liang , Zhenmei Shi , Zhao Song

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

In the classical transformer attention scheme, we are given three $n \times d$ size matrices $Q, K, V$ (the query, key, and value tokens), and the goal is to compute a new $n \times d$ size matrix $D^{-1} \exp(QK^\top) V$ where $D =…

Data Structures and Algorithms · Computer Science 2023-10-09 Josh Alman , Zhao Song

Transformer architectures have led to remarkable progress in many state-of-art applications. However, despite their successes, modern transformers rely on the self-attention mechanism, whose time- and space-complexity is quadratic in the…

Machine Learning · Computer Science 2022-09-13 Feyza Duman Keles , Pruthuvi Mahesakya Wijewardena , Chinmay Hegde

Large language model (LLM) inference demands significant amount of computation and memory, especially in the key attention mechanism. While techniques, such as quantization and acceleration algorithms, like FlashAttention, have improved…

Machine Learning · Computer Science 2024-12-18 Hao Kang , Srikant Bharadwaj , James Hensman , Tushar Krishna , Victor Ruhle , Saravan Rajmohan

The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large language models efficiently. For this approach, there has been significant research into…

Computation and Language · Computer Science 2026-05-26 Spandan Pratyush

Recent studies reveal the potential of recurrent neural network transducer (RNN-T) for end-to-end (E2E) speech recognition. Among some most popular E2E systems including RNN-T, Attention Encoder-Decoder (AED), and Connectionist Temporal…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-19 Bin Wang , Yan Yin , Hui Lin