English
Related papers

Related papers: Decomposing Query-Key Feature Interactions Using C…

200 papers

Cross-attention is a core mechanism in encoder-decoder architectures, widespread in many fields, including speech-to-text (S2T) processing. Its scores have been repurposed for various downstream applications--such as timestamp estimation…

Computation and Language · Computer Science 2025-09-23 Sara Papi , Dennis Fucci , Marco Gaido , Matteo Negri , Luisa Bentivogli

In the Transformer model, "self-attention" combines information from attended embeddings into the representation of the focal embedding in the next layer. Thus, across layers of the Transformer, information originating from different tokens…

Machine Learning · Computer Science 2020-06-02 Samira Abnar , Willem Zuidema

The size of the key-value (KV) cache plays a critical role in determining both the maximum context length and the number of concurrent requests supported during inference in modern language models. The KV cache size grows proportionally…

Computation and Language · Computer Science 2024-09-24 Shashank Rajput , Ying Sheng , Sean Owen , Vitaliy Chiley

Convolutional Neural Networks have achieved impressive results in various tasks, but interpreting the internal mechanism is a challenging problem. To tackle this problem, we exploit a multi-channel attention mechanism in feature space. Our…

Computer Vision and Pattern Recognition · Computer Science 2019-05-22 Masanari Kimura , Masayuki Tanaka

With the attention mechanism, transformers achieve significant empirical successes. Despite the intuitive understanding that transformers perform relational inference over long sequences to produce desirable representations, we lack a…

Machine Learning · Computer Science 2024-04-02 Yufeng Zhang , Boyi Liu , Qi Cai , Lingxiao Wang , Zhaoran Wang

The Key-Value (KV) cache is central to the efficiency of transformer-based large language models (LLMs), storing previously computed vectors to accelerate inference. Yet, as sequence length and batch size grow, the cache becomes a major…

Machine Learning · Computer Science 2025-12-08 Damien Lesens , Beheshteh T. Rakhshan , Guillaume Rabusseau

The Transformer model architecture has become one of the most widely used in deep learning and the attention mechanism is at its core. The standard attention formulation uses a softmax operation applied to a scaled dot product between query…

Machine Learning · Computer Science 2026-04-02 Hariprasath Govindarajan , Per Sidén , Jacob Roll , Fredrik Lindsten

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

In recommender systems, models mostly use a combination of embedding layers and multilayer feedforward neural networks. The high-dimensional sparse original features are downscaled in the embedding layer and then fed into the fully…

Information Retrieval · Computer Science 2022-05-19 Mohan Hasama , Jing Li

The attention mechanism is a fundamental component of the Transformer model, contributing to interactions among distinct tokens, in contrast to earlier feed-forward neural networks. In general, the attention scores are determined simply by…

Computation and Language · Computer Science 2024-10-11 Chuanyang Zheng , Yihang Gao , Han Shi , Jing Xiong , Jiankai Sun , Jingyao Li , Minbin Huang , Xiaozhe Ren , Michael Ng , Xin Jiang , Zhenguo Li , Yu Li

Semantic correspondence is the problem of establishing correspondences across images depicting different instances of the same object or scene class. One of recent approaches to this problem is to estimate parameters of a global…

Computer Vision and Pattern Recognition · Computer Science 2018-10-29 Paul Hongsuck Seo , Jongmin Lee , Deunsol Jung , Bohyung Han , Minsu Cho

Existing attention mechanisms either attend to local image grid or object level features for Visual Question Answering (VQA). Motivated by the observation that questions can relate to both object instances and their parts, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2021-08-30 Moshiur R Farazi , Salman H Khan

Over recent years, the Transformer has become a fundamental building block for sequence modeling architectures. Yet at its core is the use of self-attention, whose memory and computational cost grow quadratically with the sequence length…

Machine Learning · Computer Science 2025-04-02 Qiuhao Zeng , Jerry Huang , Peng Lu , Gezheng Xu , Boxing Chen , Charles Ling , Boyu Wang

The Transformer is a sequence model that forgoes traditional recurrent architectures in favor of a fully attention-based approach. Besides improving performance, an advantage of using attention is that it can also help to interpret a model…

Human-Computer Interaction · Computer Science 2019-06-14 Jesse Vig

Understanding relationships between attention heads is essential for interpreting the internal structure of Transformers, yet existing metrics do not capture this structure well. We focus on the subspaces spanned by attention-head weight…

Computation and Language · Computer Science 2026-01-16 Hiroaki Yamagiwa , Yusuke Takase , Hidetoshi Shimodaira

The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by…

Computation and Language · Computer Science 2021-09-13 Hongfei Xu , Qiuhui Liu , Josef van Genabith , Deyi Xiong

Pairwise dot product-based attention allows Transformers to exchange information between tokens in an input-dependent way, and is key to their success across diverse applications in language and vision. However, a typical Transformer model…

With recent advancements in deep learning methods, automatically learning deep features from the original data is becoming an effective and widespread approach. However, the hand-crafted expert knowledge-based features are still insightful.…

Machine Learning · Computer Science 2021-05-10 Guanjie Huang , Fenglong Ma

In this paper we delve deep in the Transformer architecture by investigating two of its core components: self-attention and contextual embeddings. In particular, we study the identifiability of attention weights and token embeddings, and…

Computation and Language · Computer Science 2020-02-10 Gino Brunner , Yang Liu , Damián Pascual , Oliver Richter , Massimiliano Ciaramita , Roger Wattenhofer

This prospective study proposes CoMatch, a novel semi-dense image matcher with dynamic covisibility awareness and bilateral subpixel accuracy. Firstly, observing that modeling context interaction over the entire coarse feature map elicits…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Zizhuo Li , Yifan Lu , Linfeng Tang , Shihua Zhang , Jiayi Ma