English
Related papers

Related papers: KiToke: Kernel-based Interval-aware Token Compress…

200 papers

Large Vision-Language Models (LVLMs) rely on dense visual tokens to capture fine-grained visual information, but processing all these tokens incurs substantial computational and memory overhead during inference. To address this issue, we…

Machine Learning · Computer Science 2026-03-24 Xu Li , Yi Zheng , Yuxuan Liang , Zhe Liu , Xiaolei Chen , Haotian Chen , Rui Zhu , Xiangyang Xue

Video Large Language Models (VLLMs) excel in video understanding, but their excessive visual tokens pose a significant computational challenge for real-world applications. Current methods aim to enhance inference efficiency by visual token…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Junpeng Ma , Qizhe Zhang , Ming Lu , Zhibin Wang , Qiang Zhou , Jun Song , Shanghang Zhang

Recent Vision-Language Models (VLMs) have demonstrated remarkable multimodal understanding capabilities, yet the redundant visual tokens incur prohibitive computational overhead and degrade inference efficiency. Prior studies typically…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Qiankun Ma , Ziyao Zhang , Haofei Wang , Jie Chen , Zhen Song , Hairong Zheng

With the development of large language models (LLMs), efficient inference through Key-Value (KV) cache compression has attracted considerable attention, especially for long-context generation. To compress the KV cache, recent methods…

Computation and Language · Computer Science 2025-10-28 Qingyue Yang , Jie Wang , Xing Li , Zhihai Wang , Chen Chen , Lei Chen , Xianzhi Yu , Wulong Liu , Jianye Hao , Mingxuan Yuan , Bin Li

Vision-Language Models (VLMs) process thousands of visual tokens per image alongside comparatively few text tokens, yet existing compression methods treat both modalities uniformly. We observe that the two modalities have fundamentally…

Machine Learning · Computer Science 2026-05-29 Yilin Feng , Ahmed Burak Gulhan , Mahmut Taylan Kandemir

Vision-language models (VLMs) have recently expanded from static image understanding to video reasoning, but their scalability is fundamentally limited by the quadratic cost of processing dense frame sequences. Long videos often exceed the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-17 Natan Bagrov , Eugene Khvedchenia , Borys Tymchenko , Shay Aharon , Lior Kadoch , Tomer Keren , Ofri Masad , Yonatan Geifman , Ran Zilberstein , Tuomas Rintamaki , Matthieu Le , Andrew Tao

We propose AdapTok, an adaptive temporal causal video tokenizer that can flexibly allocate tokens for different frames based on video content. AdapTok is equipped with a block-wise masking strategy that randomly drops tail tokens of each…

Computer Vision and Pattern Recognition · Computer Science 2025-10-15 Yan Li , Changyao Tian , Renqiu Xia , Ning Liao , Weiwei Guo , Junchi Yan , Hongsheng Li , Jifeng Dai , Hao Li , Xue Yang

In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead. To address this, recent studies have explored pruning redundant or less informative visual…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Sangin Lee , Yukyung Choi

Despite achieving remarkable performance on various vision-language tasks, Transformer-based Vision-Language Models (VLMs) suffer from redundancy in inputs and parameters, significantly hampering their efficiency in real-world applications.…

Computation and Language · Computer Science 2024-02-27 Zekun Wang , Jingchang Chen , Wangchunshu Zhou , Haichao Zhu , Jiafeng Liang , Liping Shan , Ming Liu , Dongliang Xu , Qing Yang , Bing Qin

This paper presents VideoLoom, a unified Video Large Language Model (Video LLM) for joint spatial-temporal understanding. To facilitate the development of fine-grained spatial and temporal localization capabilities, we curate LoomData-8.7k,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Jiapeng Shi , Junke Wang , Zuyao You , Bo He , Zuxuan Wu

Omnimodal large language models (Omni-LLMs) show strong capability in audio-video understanding, but their practical deployment remains limited by high inference cost of long video streams and dense audio sequences. Despite recent progress,…

Artificial Intelligence · Computer Science 2026-05-13 Yuchen Deng , Zidang Cai , Hai-Tao Zheng , Jie Wang , Feidiao Yang , Yuxing Han

Multimodal Large Language Models have demonstrated remarkable capabilities in video understanding, yet face prohibitive computational costs and performance degradation from ''context rot'' due to massive visual token redundancy. Existing…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Shida Wang , YongXiang Hua , Zhou Tao , Haoyu Cao , Linli Xu

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

Large Multimodal Models (LMMs) uniformly perceive video frames, creating computational inefficiency for videos with inherently varying temporal information density. This paper present \textbf{Quicksviewer}, an LMM with new perceiving…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Ji Qi , Yuan Yao , Yushi Bai , Bin Xu , Juanzi Li , Zhiyuan Liu , Tat-Seng Chua

Omni-modal large language models have demonstrated remarkable potential in holistic multimodal understanding; however, the token explosion caused by high-resolution audio and video inputs remains a critical bottleneck for real-time…

Artificial Intelligence · Computer Science 2026-05-15 Yeo Jeong Park , Hyemi Jang , Minseo Choi , Jongsun Lee , Jooyoung Choi , Yongkweon Jeon

Large language models (LLMs) enable long-context tasks but face efficiency challenges due to the growing key-value (KV) cache. We propose LeanK, a learning-based method that prunes unimportant key (K) cache channels by leveraging static…

Machine Learning · Computer Science 2025-08-05 Yike Zhang , Zhiyuan He , Huiqiang Jiang , Chengruidong Zhang , Yuqing Yang , Jianyong Wang , Lili Qiu

This work presents VTok, a unified video tokenization framework that can be used for both generation and understanding tasks. Unlike the leading vision-language systems that tokenize videos through a naive frame-sampling strategy, we…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Feng Wang , Yichun Shi , Ceyuan Yang , Qiushan Guo , Jingxiang Sun , Alan Yuille , Peng Wang

Vision-Language Models (VLMs) demonstrate impressive performance in understanding visual content with language instruction by converting visual inputs to vision tokens. However, redundancy in vision tokens results in the degraded inference…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Sixun Dong , Juhua Hu , Mian Zhang , Ming Yin , Yanjie Fu , Qi Qian

Recent advancements in video understanding within visual large language models (VLLMs) have led to notable progress. However, the complexity of video data and contextual processing limitations still hinder long-video comprehension. A common…

Computer Vision and Pattern Recognition · Computer Science 2025-04-30 Yanan Guo , Wenhui Dong , Jun Song , Shiding Zhu , Xuan Zhang , Hanqing Yang , Yingbo Wang , Yang Du , Xianing Chen , Bo Zheng

Recent large-scale video-language pre-trained models have shown appealing performance on various downstream tasks. However, the pre-training process is computationally expensive due to the requirement of millions of video-text pairs and the…

Computer Vision and Pattern Recognition · Computer Science 2022-10-24 Dongsheng Chen , Chaofan Tao , Lu Hou , Lifeng Shang , Xin Jiang , Qun Liu