English
Related papers

Related papers: ASAP: Attention Sink Anchored Pruning

200 papers

Transformers have emerged as a competitive alternative to convnets in vision tasks, yet they lack the architectural inductive bias of convnets, which may hinder their potential performance. Specifically, Vision Transformers (ViTs) are not…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Hagay Michaeli , Daniel Soudry

Video Large Language Models (VLLMs) incur substantial prefilling cost due to the large number of visual tokens. While attention-based token pruning offers a promising acceleration strategy, applying it at shallow decoder layers often causes…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Yingjie Xia , Tao Liu , Jinglei Shi , Qingsong Xie , Heng Guo , Jian Yang , Xi Wang

Modern large vision-language models (LVLMs) convert each input image into a large set of tokens that far outnumber the text tokens. Although this improves visual perception, it also introduces severe image token redundancy. Because image…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Yanshu Li , Jianjiang Yang , Zhennan Shen , Ligong Han , Haoyan Xu , Ruixiang Tang

Shift equivariance is a fundamental principle that governs how we perceive the world - our recognition of an object remains invariant with respect to shifts. Transformers have gained immense popularity due to their effectiveness in both…

Computer Vision and Pattern Recognition · Computer Science 2023-06-14 Peijian Ding , Davit Soselia , Thomas Armstrong , Jiahao Su , Furong Huang

Vision Transformer(ViT) is now dominating many vision tasks. The drawback of quadratic complexity of its token-wise multi-head self-attention (MHSA), is extensively addressed via either token sparsification or dimension reduction (in…

Computer Vision and Pattern Recognition · Computer Science 2023-06-21 Haiyang Xu , Zhichao Zhou , Dongliang He , Fu Li , Jingdong Wang

Transformers with powerful global relation modeling abilities have been introduced to fundamental computer vision tasks recently. As a typical example, the Vision Transformer (ViT) directly applies a pure transformer architecture on image…

Computer Vision and Pattern Recognition · Computer Science 2021-08-05 Xiaoyu Yue , Shuyang Sun , Zhanghui Kuang , Meng Wei , Philip Torr , Wayne Zhang , Dahua Lin

Vision transformers (ViTs) have gained popularity recently. Even without customized image operators such as convolutions, ViTs can yield competitive performance when properly trained on massive data. However, the computational overhead of…

Machine Learning · Computer Science 2022-03-17 Shixing Yu , Tianlong Chen , Jiayi Shen , Huan Yuan , Jianchao Tan , Sen Yang , Ji Liu , Zhangyang Wang

First-person dynamic spatial reasoning requires models to track continuous motion and precise geometric structure, but the quadratic attention cost of Transformer-based Video-LLMs makes dense visual tokens computationally expensive.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Pengtao Ma , Ziliang Zhou , Ciyu Ruan , Haoyang Wang , Kaiyuan Li , Zihang Gong , Wenhua Ding , Chen Gao , Jingao Xu , Xinlei Chen

The attention module in vision transformers(ViTs) performs intricate spatial correlations, contributing significantly to accuracy and delay. It is thereby important to modulate the number of attentions according to the input feature…

Hardware Architecture · Computer Science 2024-04-24 Abhishek Moitra , Abhiroop Bhattacharjee , Priyadarshini Panda

In this work, to limit the number of required attention inference hops in memory-augmented neural networks, we propose an online adaptive approach called A2P-MANN. By exploiting a small neural network classifier, an adequate number of…

Computation and Language · Computer Science 2022-02-24 Mohsen Ahmadzadeh , Mehdi Kamal , Ali Afzali-Kusha , Massoud Pedram

Loss of plasticity refers to the progressive inability of a model to adapt to new tasks and poses a fundamental challenge for continual learning. While this phenomenon has been extensively studied in homogeneous neural architectures, such…

Machine Learning · Computer Science 2026-03-10 Caihao Sun , Mingqi Yuan , Shiyuan Wang , Jiayu Chen

Camouflaged Object Detection (COD) aims to segment targets that share extreme textural and structural similarities with their complex environments. Leveraging their capacity for long-range dependency modeling, Transformer-based detectors…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Yuhan Gao , Shuhao Kang , Xin He , Bing Li , Xu Cheng , Yun Liu

Recently, vision transformers (ViTs) have achieved excellent performance on vision tasks by measuring the global self-attention among the image patches. Given $n$ patches, they will have quadratic complexity such as $\mathcal{O}(n^2)$ and…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Jiquan Shan , Junxiao Wang , Lifeng Zhao , Liang Cai , Hongyuan Zhang , Ioannis Liritzis

Vision-Language Models (VLMs) have revolutionized multi-modal learning by jointly processing visual and textual information. Yet, they face significant challenges due to the high computational and memory demands of processing long sequences…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Yvon Apedo , Martyna Poreba , Michal Szczepanski , Samia Bouchafa

In this work, we present FastAV, the first token pruning framework tailored for audio-visual large language models (AV-LLMs). While token pruning has been actively explored in standard large language models (LLMs) and vision-language models…

Machine Learning · Computer Science 2026-01-21 Chaeyoung Jung , Youngjoon Jang , Seungwoo Lee , Joon Son Chung

Modern Search Engine Results Pages (SERPs) present complex layouts where multiple elements compete for visibility. Attention modelling is crucial for optimising web design and computational advertising, whereas attention metrics can inform…

Information Retrieval · Computer Science 2025-05-08 Mario Villaizán-Vallelado , Matteo Salvatori , Kayhan Latifzadeh , Antonio Penta , Luis A. Leiva , Ioannis Arapakis

Recently, Transformers have shown promising performance in various vision tasks. However, the high costs of global self-attention remain challenging for Transformers, especially for high-resolution vision tasks. Inspired by one of the most…

Computer Vision and Pattern Recognition · Computer Science 2023-11-13 Zhemin Zhang , Xun Gong

Generative recommendation systems typically leverage Semantic Identifiers (SIDs), which represent each item as a sequence of tokens that encode semantic information. However, representing item ID with multiple SIDs significantly increases…

Information Retrieval · Computer Science 2026-01-27 Tianyu Zhan , Kairui Fu , Zheqi Lv , Shengyu Zhang

This paper investigates the role of attention heads in CLIP's image encoder. Building on interpretability studies, we conduct an exhaustive analysis and find that certain heads, distributed across layers, are detrimental to the resulting…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Feng Lin , Marco Chen , Haokui Zhang , Xiaotian Yu , Guangming Lu , Rong Xiao

Vision transformers (ViTs) have been successfully applied in image classification tasks recently. In this paper, we show that, unlike convolution neural networks (CNNs)that can be improved by stacking more convolutional layers, the…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Daquan Zhou , Bingyi Kang , Xiaojie Jin , Linjie Yang , Xiaochen Lian , Zihang Jiang , Qibin Hou , Jiashi Feng