English
Related papers

Related papers: METok: Multi-Stage Event-based Token Compression f…

200 papers

Multi-modal large language models (MLLMs) have achieved remarkable capabilities by integrating visual perception with language understanding, enabling applications such as image-grounded dialogue, visual question answering, and scientific…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Tianyi Bai , Zengjie Hu , Fupeng Sun , Jiantao Qiu , Yizhen Jiang , Guangxin He , Bohan Zeng , Conghui He , Binhang Yuan , Wentao Zhang

Long video understanding is a complex task that requires both spatial detail and temporal awareness. While Vision-Language Models (VLMs) obtain frame-level understanding capabilities through multi-frame input, they suffer from information…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Ziyi Wang , Haoran Wu , Yiming Rong , Deyang Jiang , Yixin Zhang , Yunlong Zhao , Shuang Xu , Bo 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

Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present a significant bottleneck for current tokenizers, which…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Haotian Ye , Qiyuan He , Jiaqi Han , Puheng Li , Jiaojiao Fan , Zekun Hao , Fitsum Reda , Yogesh Balaji , Huayu Chen , Sheng Liu , Angela Yao , James Zou , Stefano Ermon , Haoxiang Wang , Ming-Yu Liu

Recent advances in Large Language Models (LLMs) have led to significant breakthroughs in video understanding. However, existing models still struggle with long video processing due to the context length constraint of LLMs and the vast…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Haoran Hao , Jiaming Han , Yiyuan Zhang , Xiangyu Yue

Autoregressive (AR) video generative models rely on video tokenizers that compress pixels into discrete token sequences. The length of these token sequences is crucial for balancing reconstruction quality against downstream generation…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Tianwei Xiong , Jun Hao Liew , Zilong Huang , Zhijie Lin , Jiashi Feng , Xihui Liu

Efficient video tokenization remains a key bottleneck in learning general purpose vision models that are capable of processing long video sequences. Prevailing approaches are restricted to encoding videos to a fixed number of tokens, where…

Machine Learning · Computer Science 2025-02-04 Wilson Yan , Volodymyr Mnih , Aleksandra Faust , Matei Zaharia , Pieter Abbeel , Hao Liu

Video Large Language Models (VLLMs) demonstrate strong video understanding but suffer from inefficiency due to redundant visual tokens. Existing pruning primary targets intra-frame spatial redundancy or prunes inside the LLM with…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Jinlong Li , Liyuan Jiang , Haonan Zhang , Nicu Sebe

This paper presents VideoStreaming, an advanced vision-language large model (VLLM) for video understanding, that capably understands arbitrary-length video with a constant number of video tokens streamingly encoded and adaptively selected.…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Rui Qian , Xiaoyi Dong , Pan Zhang , Yuhang Zang , Shuangrui Ding , Dahua Lin , Jiaqi Wang

Video-based multimodal large language models (Video-LLMs) possess significant potential for video understanding tasks. However, most Video-LLMs treat videos as a sequential set of individual frames, which results in insufficient…

Computer Vision and Pattern Recognition · Computer Science 2024-10-16 Xiaohan Lan , Yitian Yuan , Zequn Jie , Lin Ma

Rapid advances in Large Language Models (LLMs) have spurred demand for processing extended context sequences in contemporary applications. However, this progress faces two challenges: performance degradation due to sequence lengths…

Computation and Language · Computer Science 2025-10-10 Wei Wu , Zhuoshi Pan , Chao Wang , Liyi Chen , Yunchu Bai , Tianfu Wang , Kun Fu , Zheng Wang , Hui Xiong

Despite advanced token compression techniques, existing multimodal large language models (MLLMs) still struggle with hour-long video understanding. In this work, we propose Video-XL-Pro, an efficient method for extremely long video…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Xiangrui Liu , Yan Shu , Zheng Liu , Ao Li , Yang Tian , Bo Zhao

Long-form video understanding, characterized by long-range temporal dependencies and multiple events, remains a challenge. Existing methods often rely on static reasoning or external visual-language models (VLMs), which face issues like…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Yuan Xie , Tianshui Chen , Zheng Ge , Lionel Ni

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

Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in processing vision-language tasks. One of the crux of MLLMs lies in vision tokenization, which involves efficiently transforming input visual signals into…

Computer Vision and Pattern Recognition · Computer Science 2025-02-27 Shengqiong Wu , Hao Fei , Xiangtai Li , Jiayi Ji , Hanwang Zhang , Tat-Seng Chua , Shuicheng Yan

Omni-modal large language models (om-LLMs) achieve unified audio-visual understanding by encoding video and audio into temporally aligned token sequences interleaved at the window level. However, processing these dense non-textual tokens…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Zijie Xin , Jie Yang , Ruixiang Zhao , Tianyi Wang , Fengyun Rao , Jing Lyu , Xirong Li

The excessive use of visual tokens in existing Multimoal Large Language Models (MLLMs) often exhibits obvious redundancy and brings in prohibitively expensive computation. To gain insights into this problem, we first conduct extensive…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Qiong Wu , Wenhao Lin , Yiyi Zhou , Weihao Ye , Zhanpeng Zen , Xiaoshuai Sun , Rongrong Ji

Multimodal large language models (MLLMs) have made remarkable strides, largely driven by their ability to process increasingly long and complex contexts, such as high-resolution images, extended video sequences, and lengthy audio input.…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Kele Shao , Keda Tao , Kejia Zhang , Sicheng Feng , Mu Cai , Yuzhang Shang , Haoxuan You , Can Qin , Yang Sui , Huan Wang

Action recognition and localization in complex, untrimmed videos remain a formidable challenge in computer vision, largely due to the limitations of existing methods in capturing fine-grained actions, long-term temporal dependencies, and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Liyang Peng , Sihan Zhu , Yunjie Guo

Adapting Multimodal Large Language Models (MLLMs) for hour-long videos is bottlenecked by context limits. Dense visual streams saturate token budgets and exacerbate the lost-in-the-middle phenomenon. Existing heuristics, like sparse…