English
Related papers

Related papers: Cascaded Head-colliding Attention

200 papers

Transformer-based large language models (LLMs) excel in natural language processing tasks by capturing long-range dependencies through self-attention mechanisms. However, long-context modeling faces significant computational inefficiencies…

Computation and Language · Computer Science 2025-08-15 Shuhai Zhang , Zeng You , Yaofo Chen , Zhiquan Wen , Qianyue Wang , Zhijie Qiu , Yuanqing Li , Mingkui Tan

Vision Transformers are very popular nowadays due to their state-of-the-art performance in several computer vision tasks, such as image classification and action recognition. Although their performance has been greatly enhanced through…

Computer Vision and Pattern Recognition · Computer Science 2024-10-28 Dimitrios Konstantinidis , Ilias Papastratis , Kosmas Dimitropoulos , Petros Daras

Multimodal learning, which integrates data from diverse sensory modes, plays a pivotal role in artificial intelligence. However, existing multimodal learning methods often struggle with challenges where some modalities appear more dominant…

Machine Learning · Computer Science 2024-04-02 Xiaohui Zhang , Jaehong Yoon , Mohit Bansal , Huaxiu Yao

Tabular data inherently exhibits significant feature heterogeneity, but existing transformer-based methods lack specialized mechanisms to handle this property. To bridge the gap, we propose MAYA, an encoder-decoder transformer-based…

Machine Learning · Computer Science 2025-09-23 Xuechen Li , Yupeng Li , Jian Liu , Xiaolin Jin , Xin Hu

Since the Transformer architecture was introduced in 2017 there has been many attempts to bring the self-attention paradigm in the field of computer vision. In this paper we propose a novel self-attention module that can be easily…

Computer Vision and Pattern Recognition · Computer Science 2021-11-19 Roberto Pecoraro , Valerio Basile , Viviana Bono , Sara Gallo

Existing text- and image-based multimodal dialogue systems use the traditional Hierarchical Recurrent Encoder-Decoder (HRED) framework, which has an utterance-level encoder to model utterance representation and a context-level encoder to…

Computation and Language · Computer Science 2021-10-22 Rongyi Sun , Borun Chen , Qingyu Zhou , Yinghui Li , YunBo Cao , Hai-Tao Zheng

Initially developed for natural language processing (NLP), Transformer model is now widely used for speech processing tasks such as speaker recognition, due to its powerful sequence modeling capabilities. However, conventional…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-28 Rui Wang , Junyi Ao , Long Zhou , Shujie Liu , Zhihua Wei , Tom Ko , Qing Li , Yu Zhang

Sequence-to-sequence models with soft attention have been successfully applied to a wide variety of problems, but their decoding process incurs a quadratic time and space cost and is inapplicable to real-time sequence transduction. To…

Computation and Language · Computer Science 2018-02-26 Chung-Cheng Chiu , Colin Raffel

Personality computing and affective computing have gained recent interest in many research areas. The datasets for the task generally have multiple modalities like video, audio, language and bio-signals. In this paper, we propose a flexible…

Computer Vision and Pattern Recognition · Computer Science 2023-01-13 Tanay Agrawal , Dhruv Agarwal , Michal Balazia , Neelabh Sinha , Francois Bremond

Transformer model has been widely used on machine translation tasks and obtained state-of-the-art results. In this paper, we report an interesting phenomenon in its encoder-decoder multi-head attention: different attention heads of the…

Computation and Language · Computer Science 2019-11-22 Zewei Sun , Shujian Huang , Hao-Ran Wei , Xin-yu Dai , Jiajun Chen

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

Self-attention and position embedding are two key modules in transformer-based Large Language Models (LLMs). However, the potential relationship between them is far from well studied, especially for long context window extending. In fact,…

Machine Learning · Computer Science 2024-02-29 Shiyi Zhu , Jing Ye , Wei Jiang , Siqiao Xue , Qi Zhang , Yifan Wu , Jianguo Li

As the development of Large Language Models (LLMs) shifts from parameter scaling to inference-time collaboration, the Mixture-of-Agents (MoA) framework has emerged as a general paradigm to harness collective intelligence by layering diverse…

Computation and Language · Computer Science 2026-01-26 Jianyu Wen , Yang Wei , Xiongxi Yu , Changxuan Xiao , Ke Zeng

Recent research has explored the memorization capacity of multi-head attention, but these findings are constrained by unrealistic limitations on the context size. We present a novel proof for language-based Transformers that extends the…

Artificial Intelligence · Computer Science 2025-03-11 Léo Dana , Muni Sreenivas Pydi , Yann Chevaleyre

The current large language models are mainly based on decode-only structure transformers, which have great in-context learning (ICL) capabilities. It is generally believed that the important foundation of its ICL capability is the induction…

Computation and Language · Computer Science 2024-12-06 Mingyu Xu , Wei Cheng , Bingning Wang , Weipeng Chen

Transformers have revolutionized deep learning in numerous fields, including natural language processing, computer vision, and audio processing. Their strength lies in their attention mechanism, which allows for the discovering of complex…

Machine Learning · Computer Science 2024-04-02 Uladzislau Yorsh , Martin Holeňa , Ondřej Bojar , David Herel

Learning algorithms become more powerful, often at the cost of increased complexity. In response, the demand for algorithms to be transparent is growing. In NLP tasks, attention distributions learned by attention-based deep learning models…

Computation and Language · Computer Science 2019-07-09 Joris Baan , Maartje ter Hoeve , Marlies van der Wees , Anne Schuth , Maarten de Rijke

The self-attention mechanism, while foundational to modern Transformer architectures, suffers from a critical inefficiency: it frequently allocates substantial attention to redundant or noisy context. Differential Attention addressed this…

State-of-the-art results on neural machine translation often use attentional sequence-to-sequence models with some form of convolution or recursion. Vaswani et al. (2017) propose a new architecture that avoids recurrence and convolution…

Artificial Intelligence · Computer Science 2017-11-08 Karim Ahmed , Nitish Shirish Keskar , Richard Socher

The attention interaction matrix $QK^{\top}$ contains two entangled computations: a skew-symmetric component that redistributes information between positions (routing) and a symmetric component that scales mutual relevance (filtering). We…

Machine Learning · Computer Science 2026-05-20 Shafayeth Jamil , Rehan Kapadia