English
Related papers

Related papers: MARC: Memory-Augmented RL Token Compression for Ef…

200 papers

Long-form video understanding is essential for various applications such as video retrieval, summarizing, and question answering. Yet, traditional approaches demand substantial computing power and are often bottlenecked by GPU memory. To…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Saket Gurukar , Asim Kadav

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

Although Multimodal Large Language Models (MLLMs) have shown remarkable potential in Visual Document Retrieval (VDR) through generating high-quality multi-vector embeddings, the substantial storage overhead caused by representing a page…

Computation and Language · Computer Science 2026-04-17 Jiahao Huo , Yu Huang , Yibo Yan , Ye Pan , Kening Zheng , Wei-Chieh Huang , Yi Cao , Mingdong Ou , Philip S. Yu , Xuming Hu

With recent advancements in video backbone architectures, combined with the remarkable achievements of large language models (LLMs), the analysis of long-form videos spanning tens of minutes has become both feasible and increasingly…

Computer Vision and Pattern Recognition · Computer Science 2026-02-23 Yuxiao Chen , Jue Wang , Zhikang Zhang , Jingru Yi , Xu Zhang , Yang Zou , Zhaowei Cai , Jianbo Yuan , Xinyu Li , Hao Yang , Davide Modolo

Online video understanding is essential for applications like public surveillance and AI glasses. However, applying Multimodal Large Language Models (MLLMs) to this domain is challenging due to the large number of video frames, resulting in…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Xinqi Jin , Hanxun Yu , Bohan Yu , Kebin Liu , Jian Liu , Keda Tao , Yixuan Pei , Huan Wang , Fan Dang , Jiangchuan Liu , Weiqiang Wang

Sparse attention mechanisms aim to reduce computational overhead with minimal accuracy loss by selectively processing salient tokens. Despite their effectiveness, most methods merely exploit a model's inherent sparsity and thus plateau at…

Machine Learning · Computer Science 2026-03-02 Feng Chen , Yefei He , Lequan Lin , Chenhui Gou , Jing Liu , Bohan Zhuang , Qi Wu

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

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

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

Current methods for Video Moment Retrieval (VMR) struggle to align complex situations involving specific environmental details, character descriptions, and action narratives. To tackle this issue, we propose a Large Language Model-guided…

Computer Vision and Pattern Recognition · Computer Science 2024-05-22 Weijia Liu , Bo Miao , Jiuxin Cao , Xuelin Zhu , Bo Liu , Mehwish Nasim , Ajmal Mian

Most multimodal large language models (MLLMs) treat visual tokens as "a sequence of text", integrating them with text tokens into a large language model (LLM). However, a great quantity of visual tokens significantly increases the demand…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Dongchen Lu , Yuyao Sun , Zilu Zhang , Leping Huang , Jianliang Zeng , Mao Shu , Huo Cao

The past few years have witnessed increasing interests in applying deep learning to video compression. However, the existing approaches compress a video frame with only a few number of reference frames, which limits their ability to fully…

Image and Video Processing · Electrical Eng. & Systems 2021-03-18 Ren Yang , Fabian Mentzer , Luc Van Gool , Radu Timofte

Multimodal large language models (MLLMs) demonstrate strong performance across visual tasks, but their efficiency is hindered by significant computational and memory demands from processing long contexts in multimodal inputs. To address…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Yingen Liu , Fan Wu , Ruihui Li , Zhuo Tang , Kenli Li

Recent advances in Video Large Language Models (VLLMs) have significantly enhanced their ability to understand video content. Nonetheless, processing long videos remains challenging due to high computational demands and the redundancy…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Mengyue Wang , Shuo Chen , Kristian Kersting , Volker Tresp , Yunpu Ma

In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile. Our analysis reveals that the fundamental limitation lies in an inductive gap, models…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Haoyu Wang , Haonan Wang , Yuyan Chen , Jun Chen , Gang Liu , Qian Wang , Jiahong Yan , Yanghua Xiao

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

Large language models (LLMs) have demonstrated exceptional capabilities in text understanding, which has paved the way for their expansion into video LLMs (Vid-LLMs) to analyze video data. However, current Vid-LLMs struggle to…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Ming Nie , Dan Ding , Chunwei Wang , Yuanfan Guo , Jianhua Han , Hang Xu , Li Zhang

Vision-Language-Action (VLA) models have demonstrated remarkable generalization capabilities in robotic manipulation tasks, yet their substantial computational overhead remains a critical obstacle to real-world deployment. Improving…

Robotics · Computer Science 2026-02-03 Yujie Wei , Jiahan Fan , Jiyu Guo , Ruichen Zhen , Rui Shao , Xiu Su , Zeke Xie , Shuo Yang

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

The advent of real-time large multimodal models (LMMs) like GPT-4o has sparked considerable interest in efficient LMMs. LMM frameworks typically encode visual inputs into vision tokens (continuous representations) and integrate them and…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Shaolei Zhang , Qingkai Fang , Zhe Yang , Yang Feng