English
Related papers

Related papers: PoM: A Linear-Time Replacement for Attention with …

200 papers

State-of-the-art speech-to-text models typically employ Transformer-based encoders that model token dependencies via self-attention mechanisms. However, the quadratic complexity of self-attention in both memory and computation imposes…

Computation and Language · Computer Science 2026-03-03 Eva Feillet , Ryan Whetten , David Picard , Alexandre Allauzen

Diffusion models based on Multi-Head Attention (MHA) have become ubiquitous to generate high quality images and videos. However, encoding an image or a video as a sequence of patches results in costly attention patterns, as the requirements…

Computer Vision and Pattern Recognition · Computer Science 2024-11-20 David Picard , Nicolas Dufour

The self-attention mechanism, at the heart of the Transformer model, is able to effectively model pairwise interactions between tokens. However, numerous recent works have shown that it is unable to perform basic tasks involving detecting…

Machine Learning · Computer Science 2026-02-03 Sayak Chakrabarti , Toniann Pitassi , Josh Alman

Recent advances in deep neural networks have been developed via architecture search for stronger representational power. In this work, we focus on the effect of attention in general deep neural networks. We propose a simple and effective…

Computer Vision and Pattern Recognition · Computer Science 2018-07-19 Jongchan Park , Sanghyun Woo , Joon-Young Lee , In So Kweon

Modern speech processing systems rely on self-attention. Unfortunately, token mixing with self-attention takes quadratic time in the length of the speech utterance, slowing down inference and training and increasing memory consumption.…

Computation and Language · Computer Science 2024-07-12 Titouan Parcollet , Rogier van Dalen , Shucong Zhang , Sourav Bhattacharya

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

Linear sequence modeling methods, such as linear attention, state space modeling, and linear RNNs, offer significant efficiency improvements by reducing the complexity of training and inference. However, these methods typically compress the…

Computation and Language · Computer Science 2025-11-19 Jusen Du , Weigao Sun , Disen Lan , Jiaxi Hu , Yu Cheng

Recent works in dataset distillation seek to minimize training expenses by generating a condensed synthetic dataset that encapsulates the information present in a larger real dataset. These approaches ultimately aim to attain test accuracy…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Samir Khaki , Ahmad Sajedi , Kai Wang , Lucy Z. Liu , Yuri A. Lawryshyn , Konstantinos N. Plataniotis

Recently many effective attention modules are proposed to boot the model performance by exploiting the internal information of convolutional neural networks in computer vision. In general, many previous works ignore considering the design…

Machine Learning · Computer Science 2022-10-25 Shanshan Zhong , Wushao Wen , Jinghui Qin

The widespread adoption of Large Language Models (LLMs) has exponentially increased the demand for efficient serving systems. With growing requests and context lengths, key-value (KV)-related operations, including attention computation and…

Hardware Architecture · Computer Science 2026-02-13 Lian Liu , Shixin Zhao , Yutian Zhou , Yintao He , Mengdi Wang , Yinhe Han , Ying Wang

Transformer models have redefined sequence learning, yet dot-product self-attention introduces a quadratic token-mixing bottleneck for long-context time-series. We introduce the \textbf{Phasor Transformer} block, a phase-native alternative…

Machine Learning · Computer Science 2026-03-19 Dibakar Sigdel

POI representation learning plays a crucial role in handling tasks related to user mobility data. Recent studies have shown that enriching POI representations with multimodal information can significantly enhance their task performance.…

Artificial Intelligence · Computer Science 2025-03-05 Jiawei Cheng , Jingyuan Wang , Yichuan Zhang , Jiahao Ji , Yuanshao Zhu , Zhibo Zhang , Xiangyu Zhao

Transformers provide a class of expressive architectures that are extremely effective for sequence modeling. However, the key limitation of transformers is their quadratic memory and time complexity $\mathcal{O}(L^2)$ with respect to the…

Machine Learning · Computer Science 2021-10-29 Hongyu Ren , Hanjun Dai , Zihang Dai , Mengjiao Yang , Jure Leskovec , Dale Schuurmans , Bo Dai

The three existing dominant network families, i.e., CNNs, Transformers, and MLPs, differ from each other mainly in the ways of fusing spatial contextual information, leaving designing more effective token-mixing mechanisms at the core of…

Computer Vision and Pattern Recognition · Computer Science 2022-12-26 Guoqiang Wei , Zhizheng Zhang , Cuiling Lan , Yan Lu , Zhibo Chen

The quadratic time and memory complexity inherent to self-attention mechanisms, with respect to sequence length, presents a critical computational bottleneck in the training and deployment of large-scale Transformer-based language models.…

Machine Learning · Computer Science 2024-03-19 Praneeth Kacham , Vahab Mirrokni , Peilin Zhong

Pose variation is one of the key challenges in face recognition. Conventional techniques mainly focus on face frontalization or face augmentation in image space. However, transforming face images in image space is not guaranteed to preserve…

Computer Vision and Pattern Recognition · Computer Science 2021-11-24 En-Jung Tsai , Wei-Chang Yeh

We present Polynomial Attention Drop-in Replacement (PADRe), a novel and unifying framework designed to replace the conventional self-attention mechanism in transformer models. Notably, several recent alternative attention mechanisms,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Pierre-David Letourneau , Manish Kumar Singh , Hsin-Pai Cheng , Shizhong Han , Yunxiao Shi , Dalton Jones , Matthew Harper Langston , Hong Cai , Fatih Porikli

Mixture modeling is a general technique for making any simple model more expressive through weighted combination. This generality and simplicity in part explains the success of the Expectation Maximization (EM) algorithm, in which updates…

Machine Learning · Statistics 2016-03-29 Sida I. Wang , Arun Tejasvi Chaganty , Percy Liang

Linear-attention models that compress the entire input sequence into a fixed-size recurrent state offer an efficient alternative to Transformers, but their finite memory induces forgetfulness that harms retrieval-intensive tasks. To…

Computation and Language · Computer Science 2025-10-27 Mutian He , Philip N. Garner

Linear attention has emerged as a promising alternative to softmax-based attention, leveraging kernelized feature maps to reduce complexity from quadratic to linear in sequence length. However, the non-negative constraint on feature maps…

Computer Vision and Pattern Recognition · Computer Science 2025-03-05 Weikang Meng , Yadan Luo , Xin Li , Dongmei Jiang , Zheng Zhang
‹ Prev 1 2 3 10 Next ›