English
Related papers

Related papers: Knocking-Heads Attention

200 papers

Question answering (QA) models have shown rapid progress enabled by the availability of large, high-quality benchmark datasets. Such annotated datasets are difficult and costly to collect, and rarely exist in languages other than English,…

Computation and Language · Computer Science 2020-05-05 Patrick Lewis , Barlas Oğuz , Ruty Rinott , Sebastian Riedel , Holger Schwenk

Channel attention mechanisms endeavor to recalibrate channel weights to enhance representation abilities of networks. However, mainstream methods often rely solely on global average pooling as the feature squeezer, which significantly…

Computer Vision and Pattern Recognition · Computer Science 2024-03-05 Yangbo Jiang , Zhiwei Jiang , Le Han , Zenan Huang , Nenggan Zheng

Existing transformer-based image backbones typically propagate feature information in one direction from lower to higher-levels. This may not be ideal since the localization ability to delineate accurate object boundaries, is most prominent…

Computer Vision and Pattern Recognition · Computer Science 2022-07-06 Gary Leung , Jun Gao , Xiaohui Zeng , Sanja Fidler

Audio question answering (AQA) is the task of producing natural language answers when a system is provided with audio and natural language questions. In this paper, we propose neural network architectures based on self-attention and…

Computation and Language · Computer Science 2023-06-01 Parthasaarathy Sudarsanam , Tuomas Virtanen

The architecture of Vision Transformers (ViTs), particularly the Multi-head Attention (MHA) mechanism, imposes substantial hardware demands. Deploying ViTs on devices with varying constraints, such as mobile phones, requires multiple models…

Computer Vision and Pattern Recognition · Computer Science 2024-12-06 Janek Haberer , Ali Hojjat , Olaf Landsiedel

Attention mechanisms, which enable a neural network to accurately focus on all the relevant elements of the input, have become an essential component to improve the performance of deep neural networks. There are mainly two attention…

Computer Vision and Pattern Recognition · Computer Science 2021-02-02 Qing-Long Zhang Yu-Bin Yang

Multimodal learning has gained much success in recent years. However, current multimodal fusion methods adopt the attention mechanism of Transformers to implicitly learn the underlying correlation of multimodal features. As a result, the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Thanh-Dat Truong , Christophe Bobda , Nitin Agarwal , Khoa Luu

Causal effect estimation from observational data requires careful adjustment for confounding. Classical estimators such as inverse probability weighting and augmented inverse probability weighting are effective under favorable model…

Machine Learning · Statistics 2026-04-28 Lei Wang , Debashis Ghosh

Textbook Question Answering (TQA) is a complex multimodal task to infer answers given large context descriptions and abundant diagrams. Compared with Visual Question Answering (VQA), TQA contains a large number of uncommon terminologies and…

Multimedia · Computer Science 2021-12-07 Fangzhi Xu , Qika Lin , Jun Liu , Lingling Zhang , Tianzhe Zhao , Qi Chai , Yudai Pan

Supervised operator learning is an emerging machine learning paradigm with applications to modeling the evolution of spatio-temporal dynamical systems and approximating general black-box relationships between functional data. We propose a…

Machine learning force fields (MLFFs) have become essential for accurate and efficient atomistic modeling. Despite their high accuracy, most existing approaches rely on fixed angular expansions, limiting flexibility in weighting local…

Machine Learning · Computer Science 2026-02-04 Francesco Leonardi , Boris Bonev , Kaspar Riesen

Controlled generation imposes sequence-level constraints (syntax, style, safety) that depend on future tokens, making exact conditioning of an autoregressive LM intractable. Tractable surrogates such as HMMs can approximate continuation…

Computation and Language · Computer Science 2026-02-11 Gwen Yidou-Weng , Ian Li , Anji Liu , Oliver Broadrick , Yuchen Cui , Guy Van den Broeck , Benjie Wang

Scaling the effective context length is essential for advancing large language models (LLMs) toward artificial general intelligence (AGI). However, the quadratic increase in computational complexity inherent in traditional attention…

We present core attention disaggregation (CAD), a technique that improves long-context large language model training by decoupling the core attention computation, softmax(QK^T)V, from the rest of the model and executing it on a separate…

Machine Learning · Computer Science 2025-10-22 Yonghao Zhuang , Junda Chen , Bo Pang , Yi Gu , Yibo Zhu , Yimin Jiang , Ion Stoica , Eric Xing , Hao Zhang

Transformers with linear attention allow for efficient parallel training but can simultaneously be formulated as an RNN with 2D (matrix-valued) hidden states, thus enjoying linear-time inference complexity. However, linear attention…

Machine Learning · Computer Science 2024-08-28 Songlin Yang , Bailin Wang , Yikang Shen , Rameswar Panda , Yoon Kim

Attention mechanism is a significant part of Transformer models. It helps extract features from embedded vectors by adding global information and its expressivity has been proved to be powerful. Nevertheless, the quadratic complexity…

Machine Learning · Computer Science 2025-11-11 Hanwen Liu , Yixuan Ma , Shi Jin , Yuguang Wang

Continual learning is an essential capability of human cognition, yet it poses significant challenges for current deep learning models. The primary issue is that new knowledge can interfere with previously learned information, causing the…

Machine Learning · Computer Science 2025-09-19 Eric Nuertey Coleman , Luigi Quarantiello , Samrat Mukherjee , Julio Hurtado , Vincenzo Lomonaco

Multi-modal learning has shown exceptional performance in various tasks, especially in medical applications, where it integrates diverse medical information for comprehensive diagnostic evidence. However, there still are several challenges…

Machine Learning · Computer Science 2024-11-19 Lin Fan , Yafei Ou , Cenyang Zheng , Pengyu Dai , Tamotsu Kamishima , Masayuki Ikebe , Kenji Suzuki , Xun Gong

While large language models (LLMs) excel at understanding and generating plain text, they are not tailored to handle hierarchical text structures or directly predict task-specific properties such as text rating. In fact, selectively and…

Computation and Language · Computer Science 2024-10-10 Chenxi Lin , Jiayu Ren , Guoxiu He , Zhuoren Jiang , Haiyan Yu , Xiaomin Zhu

Attention patterns play a crucial role in both training and inference of large language models (LLMs). Prior works have identified individual patterns such as retrieval heads, sink heads, and diagonal traces, yet these observations remain…

Computation and Language · Computer Science 2026-01-30 Qingyue Yang , Jie Wang , Xing Li , Yinqi Bai , Xialiang Tong , Huiling Zhen , Jianye Hao , Mingxuan Yuan , Bin Li