English
Related papers

Related papers: Token Fusion: Bridging the Gap between Token Pruni…

200 papers

Transformer-based models have achieved dominant performance in numerous NLP tasks. Despite their remarkable successes, pre-trained transformers such as BERT suffer from a computationally expensive self-attention mechanism that interacts…

Computation and Language · Computer Science 2024-06-04 Jungmin Yun , Mihyeon Kim , Youngbin Kim

Pruning has emerged as a promising direction for accelerating large language model (LLM) inference, yet existing approaches often suffer from instability because they rely on offline calibration data that may not generalize across inputs.…

Computation and Language · Computer Science 2025-12-09 Jungmin Lee , Gwangeun Byeon , Yulhwa Kim , Seokin Hong

State Space Models (SSMs) have the advantage of keeping linear computational complexity compared to attention modules in transformers, and have been applied to vision tasks as a new type of powerful vision foundation model. Inspired by the…

Computer Vision and Pattern Recognition · Computer Science 2024-09-30 Zheng Zhan , Zhenglun Kong , Yifan Gong , Yushu Wu , Zichong Meng , Hangyu Zheng , Xuan Shen , Stratis Ioannidis , Wei Niu , Pu Zhao , Yanzhi Wang

Vision Transformers (ViTs) excel in semantic segmentation but demand significant computation, posing challenges for deployment on resource-constrained devices. Existing token pruning methods often overlook fundamental visual data…

Computer Vision and Pattern Recognition · Computer Science 2025-04-28 Yuanbing Ouyang , Yizhuo Liang , Qingpeng Li , Xinfei Guo , Yiming Luo , Di Wu , Hao Wang , Yushan Pan

In multi-view medical diagnosis, deep learning-based models often fuse information from different imaging perspectives to improve diagnostic performance. However, existing approaches are prone to overfitting and rely heavily on…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Jingyu Guo , Christos Matsoukas , Fredrik Strand , Kevin Smith

Vision transformers have achieved significant improvements on various vision tasks but their quadratic interactions between tokens significantly reduce computational efficiency. Many pruning methods have been proposed to remove redundant…

Computer Vision and Pattern Recognition · Computer Science 2022-11-22 Sifan Long , Zhen Zhao , Jimin Pi , Shengsheng Wang , Jingdong Wang

This paper investigates how to efficiently deploy vision transformers on edge devices for small workloads. Recent methods reduce the latency of transformer neural networks by removing or merging tokens, with small accuracy degradation.…

Machine Learning · Computer Science 2024-11-12 Nick John Eliopoulos , Purvish Jajal , James C. Davis , Gaowen Liu , George K. Thiravathukal , Yung-Hsiang Lu

Large-scale vision language (VL) models use Transformers to perform cross-modal interactions between the input text and image. These cross-modal interactions are computationally expensive and memory-intensive due to the quadratic complexity…

Computer Vision and Pattern Recognition · Computer Science 2023-05-30 Qingqing Cao , Bhargavi Paranjape , Hannaneh Hajishirzi

Increasing the throughput of the Transformer architecture, a foundational component used in numerous state-of-the-art models for vision and language tasks (e.g., GPT, LLaVa), is an important problem in machine learning. One recent and…

Vision Transformers can achieve high accuracy and strong generalization across various contexts, but their practical applicability on real-world robotic systems is limited due to their quadratic attention complexity. Recent works have…

Computer Vision and Pattern Recognition · Computer Science 2026-05-04 Fabio Montello , Ronja Güldenring , Lazaros Nalpantidis

Multi-modal Large Language Models (MLLMs) have achieved remarkable success by integrating visual and textual modalities. However, they incur significant computational overhead due to the large number of vision tokens processed, limiting…

Computation and Language · Computer Science 2025-03-11 Yizheng Sun , Yanze Xin , Hao Li , Jingyuan Sun , Chenghua Lin , Riza Batista-Navarro

Vision encoders serve as the cornerstone of multimodal understanding. Single-encoder architectures like CLIP exhibit inherent constraints in generalizing across diverse multimodal tasks, while recent multi-encoder fusion methods introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Yuchen Liu , Yaoming Wang , Bowen Shi , Xiaopeng Zhang , Wenrui Dai , Chenglin Li , Hongkai Xiong , Qi Tian

Diffusion models excel in high-fidelity image generation but face scalability limits due to transformers' quadratic attention complexity. Plug-and-play token reduction methods like ToMeSD and ToFu reduce FLOPs by merging redundant tokens in…

Machine Learning · Computer Science 2025-12-02 Wenbo Lu , Shaoyi Zheng , Yuxuan Xia , Shengjie Wang

Vision Transformers (ViTs) achieve state-of-the-art performance in semantic segmentation but are hindered by high computational and memory costs. To address this, we propose STEP (SuperToken and Early-Pruning), a hybrid token-reduction…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Michal Szczepanski , Martyna Poreba , Karim Haroun

Vision-language models (VLMs) excel at image understanding tasks, but the large number of visual tokens imposes significant computational costs, hindering deployment on mobile devices. Many pruning methods rely solely on token importance…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Zhenkai Wu , Xiaowen Ma , Zhenliang Ni , Dengming Zhang , Han Shu , Xin Jiang , Xinghao Chen

In-context generation significantly enhances Diffusion Transformers (DiTs) by enabling controllable image-to-image generation through reference examples. However, the resulting input concatenation drastically increases sequence length,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Junqing Lin , Xingyu Zheng , Pei Cheng , Bin Fu , Jingwei Sun , Guangzhong Sun

Multimodal Large Language Models (MLLMs) have shown strong reasoning ability, but their high computational and memory costs hinder deployment in resource-constrained settings. While Post-Training Quantization (PTQ) and vision token pruning…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Xinhao Wang , Zhonyu Xia , Zhiwei Lin , Zhe Li , Yongtao Wang

Since the introduction of the Vision Transformer (ViT), researchers have sought to make ViTs more efficient by removing redundant information in the processed tokens. While different methods have been explored to achieve this goal, we still…

Computer Vision and Pattern Recognition · Computer Science 2023-08-10 Joakim Bruslund Haurum , Sergio Escalera , Graham W. Taylor , Thomas B. Moeslund

Large Vision-Language Models (LVLMs) incur high computational costs due to significant redundancy in their visual tokens. To effectively reduce this cost, researchers have proposed various visual token pruning methods. However, existing…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Wen Luo , Peng Chen , Xiaotao Huang , LiQun Huang

Self-attention and transformers have been widely used in deep learning. Recent efforts have been devoted to incorporating transformer blocks into different neural architectures, including those with convolutions, leading to various visual…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Yancheng Wang , Yingzhen Yang