English
Related papers

Related papers: When Less is Enough: Adaptive Token Reduction for …

200 papers

Vision Transformers (ViT) have achieved remarkable success in large-scale image recognition. They split every 2D image into a fixed number of patches, each of which is treated as a token. Generally, representing an image with more tokens…

Computer Vision and Pattern Recognition · Computer Science 2021-10-27 Yulin Wang , Rui Huang , Shiji Song , Zeyi Huang , Gao Huang

Understanding how Large Language Models (LLMs) process information from prompts remains a significant challenge. To shed light on this "black box," attention visualization techniques have been developed to capture neuron-level perceptions…

In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks. Each token is then mapped to an embedding, enabling parallel attention computations…

Machine Learning · Computer Science 2026-01-14 Zhenglun Kong , Yize Li , Fanhu Zeng , Lei Xin , Shvat Messica , Xue Lin , Pu Zhao , Manolis Kellis , Hao Tang , Marinka Zitnik

Vision Transformers have demonstrated exceptional performance across various computer vision tasks, yet their quadratic computational complexity concerning token length remains a significant challenge. To address this, token reduction…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Dong-Jae Lee , Jiwan Hur , Jaehyun Choi , Jaemyung Yu , Junmo Kim

The success of VLMs often relies on the dynamic high-resolution schema that adaptively augments the input images to multiple crops, so that the details of the images can be retained. However, such approaches result in a large number of…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Jiayi Han , Liang Du , Yiwen Wu , Xiangguo Zhou , Hongwei Du , Weibo Zheng

Most existing vision encoders map images into a fixed-length sequence of tokens, overlooking the fact that different images contain varying amounts of information. For example, a visually complex image (e.g., a cluttered room) inherently…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Lingjun Mao , Rodolfo Corona , Xin Liang , Wenhao Yan , Zineng Tang

Large Vision Language Models show impressive performance across image and video understanding tasks, yet their computational cost grows rapidly with the number of visual tokens. Existing token pruning methods mitigate this issue through…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Dong-Jae Lee , Sunghyun Baek , Junmo Kim

We introduce a novel visual tokenization framework that embeds a provable PCA-like structure into the latent token space. While existing visual tokenizers primarily optimize for reconstruction fidelity, they often neglect the structural…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Xin Wen , Bingchen Zhao , Ismail Elezi , Jiankang Deng , Xiaojuan Qi

In this paper we propose augmenting Vision Transformer models with learnable memory tokens. Our approach allows the model to adapt to new tasks, using few parameters, while optionally preserving its capabilities on previously learned tasks.…

Computer Vision and Pattern Recognition · Computer Science 2022-03-31 Mark Sandler , Andrey Zhmoginov , Max Vladymyrov , Andrew Jackson

Vision Transformers (ViTs) have achieved state-of-the-art performance across various computer vision tasks, but their high computational cost remains a challenge. Token pruning has been proposed to reduce this cost by selectively removing…

Sound · Computer Science 2025-10-27 Taehan Lee , Hyukjun Lee

Multi-modal large language models (MLLMs) utilizing instruction-following data, such as LLaVA, have achieved great progress in the industry. A major limitation in these models is that visual tokens consume a substantial portion of the…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Ke Wang , Hong Xuan

Recent Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language understanding tasks, yet their inference efficiency is often hampered by the large number of visual tokens, particularly in…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Jiafei Song , Fengwei Zhou , Jin Qu , Wenjin Jason Li , Tong Wu , Gengjian Xue , Zhikang Zhao , Daomin Wei , Yichao Lu , Bailin Na

Vision-Language Models (VLMs) have recently demonstrated remarkable capabilities in visual understanding and reasoning, but they also impose significant computational burdens due to long visual sequence inputs. Recent works address this…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Rinyoichi Takezoe , Yaqian Li , Zihao Bo , Anzhou Hou , Mo Guang , Kaiwen Long

Multimodal Large Language Models (MLLMs) incur significant computational cost from processing numerous vision tokens through all LLM layers. Prior pruning methods operate either before the LLM, limiting generality due to diverse…

Computer Vision and Pattern Recognition · Computer Science 2026-02-16 Omer Faruk Deniz , Ruiyu Mao , Ruochen Li , Yapeng Tian , Latifur Khan

Current vision systems typically assign fixed-length representations to images, regardless of the information content. This contrasts with human intelligence - and even large language models - which allocate varying representational…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Shivam Duggal , Phillip Isola , Antonio Torralba , William T. Freeman

Large multimodal models (LMMs) often suffer from severe inference inefficiency due to the large number of visual tokens introduced by image encoders. While recent token compression methods, such as pruning and merging, have shown promise in…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Tianfan Peng , Yuntao Du , Pengzhou Ji , Shijie Dong , Kailin Jiang , Mingchuan Ma , Yijun Tian , Jinhe Bi , Qian Li , Wei Du , Feng Xiao , Lizhen Cui

In image retrieval, deep local features learned in a data-driven manner have been demonstrated effective to improve retrieval performance. To realize efficient retrieval on large image database, some approaches quantize deep local features…

Image and Video Processing · Electrical Eng. & Systems 2021-12-14 Hui Wu , Min Wang , Wengang Zhou , Yang Hu , Houqiang Li

Efficient inference in Large Vision-Language Models is constrained by the high cost of processing thousands of visual tokens, yet it remains unclear which tokens and computations can be safely removed. While attention scores are commonly…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Samyak Jha , Junho Kim

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

Visual token reduction is critical for accelerating Vision-Language Models (VLMs), yet most existing approaches rely on a fixed budget shared across all inputs, overlooking the substantial variation in image information density. We propose…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Jialuo He , Huangxun Chen