English
Related papers

Related papers: Beyond Uniform Query Distribution: Key-Driven Grou…

200 papers

Multi-head Latent Attention (MLA), the attention used in DeepSeek-V2/V3, jointly compresses keys and values into a low-rank latent and matches the H100 roofline almost perfectly. Its trained weights, however, expose only one decoding path -…

Machine Learning · Computer Science 2026-05-28 Fanxu Meng

Grouped-Query Attention (GQA) is a widely adopted strategy for reducing the computational cost of attention layers in large language models (LLMs). However, current GQA configurations are often suboptimal because they overlook how context…

Computation and Language · Computer Science 2025-09-29 Yingfa Chen , Yutong Wu , Chenyang Song , Zhen Leng Thai , Xingyu Shen , Xu Han , Zhiyuan Liu , Maosong Sun

As question answering (QA) systems advance alongside the rapid evolution of foundation models, the need for robust, adaptable, and large-scale evaluation benchmarks becomes increasingly critical. Traditional QA benchmarks are often static…

Computation and Language · Computer Science 2025-03-10 Preetam Prabhu Srikar Dammu , Himanshu Naidu , Chirag Shah

Attention mechanism has gained huge popularity due to its effectiveness in achieving high accuracy in different domains. But attention is opportunistic and is not justified by the content or usability of the content. Transformer like…

Computer Vision and Pattern Recognition · Computer Science 2020-06-26 Chiranjib Sur

Following the major successes of self-attention and Transformers for image analysis, we investigate the use of such attention mechanisms in the context of Image Quality Assessment (IQA) and propose a novel full-reference IQA method, Vision…

Computer Vision and Pattern Recognition · Computer Science 2021-10-06 Andrei Chubarau , James Clark

The Transformer architecture has revolutionized deep learning, delivering the state-of-the-art performance in areas such as natural language processing, computer vision, and time series prediction. However, its core component,…

Machine Learning · Computer Science 2025-07-24 Haolin Jin , Mengbai Xiao , Yuan Yuan , Xiao Zhang , Dongxiao Yu , Guanghui Zhang , Haoliang Wang

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…

Machine Learning · Computer Science 2025-07-01 Venmugil Elango

Window-based attention has become a popular choice in vision transformers due to its superior performance, lower computational complexity, and less memory footprint. However, the design of hand-crafted windows, which is data-agnostic,…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Qiming Zhang , Jing Zhang , Yufei Xu , Dacheng Tao

Answer selection (answer ranking) is one of the key steps in many kinds of question answering (QA) applications, where deep models have achieved state-of-the-art performance. Among these deep models, recurrent neural network (RNN) based…

Computation and Language · Computer Science 2019-05-28 Dong Xu , Jianhui Ji , Haikuan Huang , Hongbo Deng , Wu-Jun Li

Time-series data analysis is important because numerous real-world tasks such as forecasting weather, electricity consumption, and stock market involve predicting data that vary over time. Time-series data are generally recorded over a long…

Machine Learning · Computer Science 2022-10-07 Bumjun Jung , Yusuke Mukuta , Tatsuya Harada

We propose a novel method for applying Transformer models to extractive question answering (QA) tasks. Recently, pretrained generative sequence-to-sequence (seq2seq) models have achieved great success in question answering. Contributing to…

Computation and Language · Computer Science 2021-10-14 Peng Xu , Davis Liang , Zhiheng Huang , Bing Xiang

Transformers have been proven a successful model for a variety of tasks in sequence modeling. However, computing the attention matrix, which is their key component, has quadratic complexity with respect to the sequence length, thus making…

Machine Learning · Computer Science 2020-10-01 Apoorv Vyas , Angelos Katharopoulos , François Fleuret

LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…

Machine Learning · Computer Science 2025-05-28 Ted Zadouri , Hubert Strauss , Tri Dao

After DETR was proposed, this novel transformer-based detection paradigm which performs several cross-attentions between object queries and feature maps for predictions has subsequently derived a series of transformer-based detection heads.…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Xiaohu Jiang , Ze Chen , Zhicheng Wang , Erjin Zhou , ChunYuan

Modern autoregressive models rely on attention, yet the Softmax full attention in Transformers scales quadratically with sequence length. Sliding Window Attention (SWA) achieves linear-time encoding/decoding by constraining the attention…

Machine Learning · Computer Science 2026-01-08 Jiaxu Liu , Yuhe Bai , Xiangyu Yin , Christos-Savvas Bouganis

In recent years, multi-modal transformers have shown significant progress in Vision-Language tasks, such as Visual Question Answering (VQA), outperforming previous architectures by a considerable margin. This improvement in VQA is often…

Computer Vision and Pattern Recognition · Computer Science 2022-01-12 Ankur Sikarwar , Gabriel Kreiman

Transformer-based models have been achieving state-of-the-art results in several fields of Natural Language Processing. However, its direct application to speech tasks is not trivial. The nature of this sequences carries problems such as…

Computation and Language · Computer Science 2022-05-17 Gerard Sant , Gerard I. Gállego , Belen Alastruey , Marta R. Costa-Jussà

The Transformer architecture has been successful across many domains, including natural language processing, computer vision and speech recognition. In keyword spotting, self-attention has primarily been used on top of convolutional or…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-11 Axel Berg , Mark O'Connor , Miguel Tairum Cruz

Nowadays, transformer networks have demonstrated superior performance in many computer vision tasks. In a multi-view 3D reconstruction algorithm following this paradigm, self-attention processing has to deal with intricate image tokens…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Liying Yang , Zhenwei Zhu , Xuxin Lin , Jian Nong , Yanyan Liang

Since transformer was firstly published in 2017, several works have been proposed to optimize it. However, the major structure of transformer remains unchanged, ignoring one of its main intrinsic limitations, which is the same static value…

Machine Learning · Computer Science 2025-12-30 Xiaowei Wang