English
Related papers

Related papers: Multi-Token Attention

200 papers

Large vision-language models (VLMs) typically process hundreds or thousands of visual tokens per image or video frame, incurring quadratic attention cost and substantial redundancy. Existing token reduction methods often ignore the textual…

Computer Vision and Pattern Recognition · Computer Science 2025-12-24 Kaitong Cai , Jusheng Zhang , Jing Yang , Yijia Fan , Pengtao Xie , Jian Wang , Keze Wang

Recent works show we can linearize large language models (LLMs) -- swapping the quadratic attentions of popular Transformer-based LLMs with subquadratic analogs, such as linear attention -- avoiding the expensive pretraining costs. However,…

Machine Learning · Computer Science 2025-03-07 Michael Zhang , Simran Arora , Rahul Chalamala , Alan Wu , Benjamin Spector , Aaryan Singhal , Krithik Ramesh , Christopher Ré

Attention mechanism, including global attention and local attention, plays a key role in neural machine translation (NMT). Global attention attends to all source words for word prediction. In comparison, local attention selectively looks at…

Computation and Language · Computer Science 2019-09-20 Kehai Chen , Rui Wang , Masao Utiyama , Eiichiro Sumita , Tiejun Zhao

Multi-Head Attention (MHA) is the core computational primitive underlying modern Large Language Models (LLMs). However, MHA suffers from a fundamental linear scaling limitation: $H$ attention heads produce exactly $H$ independent attention…

In this paper, we propose a novel token selective attention approach, ToSA, which can identify tokens that need to be attended as well as those that can skip a transformer layer. More specifically, a token selector parses the current…

Computer Vision and Pattern Recognition · Computer Science 2024-06-14 Manish Kumar Singh , Rajeev Yasarla , Hong Cai , Mingu Lee , Fatih Porikli

A major challenge for Multi-Agent Systems is enabling agents to adapt dynamically to diverse environments in which opponents and teammates may continually change. Agents trained using conventional methods tend to excel only within the…

Artificial Intelligence · Computer Science 2025-04-09 Qian Long , Ruoyan Li , Minglu Zhao , Tao Gao , Demetri Terzopoulos

The Softmax attention mechanism in Transformer models is notoriously computationally expensive, particularly due to its quadratic complexity, posing significant challenges in vision applications. In contrast, linear attention provides a far…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Qihang Fan , Huaibo Huang , Ran He

Multimodal Large Language Models (MLLMs) have recently demonstrated strong performance across a wide range of vision-language tasks, garnering significant attention in the computer vision. However, their efficient deployment remains a…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Ao Wang , Fengyuan Sun , Hui Chen , Zijia Lin , Jungong Han , Guiguang Ding

Answer selection and knowledge base question answering (KBQA) are two important tasks of question answering (QA) systems. Existing methods solve these two tasks separately, which requires large number of repetitive work and neglects the…

Computation and Language · Computer Science 2018-12-07 Yang Deng , Yuexiang Xie , Yaliang Li , Min Yang , Nan Du , Wei Fan , Kai Lei , Ying Shen

A standard way to evaluate the abilities of LLM involves presenting a multiple-choice question and selecting the option with the highest logit as the model's predicted answer. However, such a format for evaluating LLMs has limitations,…

Large language models with long context windows can answer complex questions directly from full-length academic, technical, and policy documents, but passing entire documents is often costly, slow, and can degrade answer quality while…

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces noisy probability distribution, which can impair effective…

Computation and Language · Computer Science 2025-11-11 Dhananjay Ram , Wei Xia , Stefano Soatto

While linear attention reduces the quadratic complexity of standard Transformers to linear time, it often lags behind in expressivity due to the removal of softmax normalization. This omission eliminates \emph{global competition}, a…

Machine Learning · Computer Science 2026-02-03 Mingwei Xu , Xuan Lin , Xinnan Guo , Wanqing Xu , Wanyun Cui

Document-level Neural Machine Translation (DocNMT) has been proven crucial for handling discourse phenomena by introducing document-level context information. One of the most important directions is to input the whole document directly to…

Computation and Language · Computer Science 2023-09-26 Zihan Liu , Zewei Sun , Shanbo Cheng , Shujian Huang , Mingxuan Wang

Transformer-based Large Language Models (LLMs) have exhibited remarkable success in extensive tasks primarily attributed to self-attention mechanism, which requires a token to consider all preceding tokens as its context to compute…

Computation and Language · Computer Science 2025-08-05 Yaofo Chen , Zeng You , Shuhai Zhang , Haokun Li , Yirui Li , Yaowei Wang , Mingkui Tan

Large Language Models (LLMs) encounter significant performance bottlenecks in long-sequence tasks due to the computational complexity and memory overhead inherent in the self-attention mechanism. To address these challenges, we introduce…

Artificial Intelligence · Computer Science 2026-02-17 Ziming Wang , Xiang Wang , Kailong Peng , Lang Qin , Juan Gabriel Kostelec , Christos Sourmpis , Axel Laborieux , Qinghai Guo

Vision-language models (VLMs) are commonly trained by directly inserting image tokens from a pretrained vision encoder into the text stream of a language model. This allows text and image information to fully attend to one another within…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Moritz Böhle , Amélie Royer , Juliette Marrie , Edouard Grave , Patrick Pérez

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

In online advertising, users may be exposed to a range of different advertising campaigns, such as natural search or referral or organic search, before leading to a final transaction. Estimating the contribution of advertising campaigns on…

Information Retrieval · Computer Science 2020-04-02 Dongdong Yang , Kevin Dyer , Senzhang Wang

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Language models (LMs) struggle to perform such reasoning consistently. We propose an approach to pinpoint and rectify multi-hop…

Computation and Language · Computer Science 2024-11-11 Mansi Sakarvadia