English
Related papers

Related papers: Fewer Tokens and Fewer Videos: Extending Video Und…

200 papers

Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention. This paper introduces NVILA, a family of open VLMs designed to jointly optimize efficiency…

We introduce SlowFast-LLaVA-1.5 (abbreviated as SF-LLaVA-1.5), a family of video large language models (LLMs) offering a token-efficient solution for long-form video understanding. We incorporate the two-stream SlowFast mechanism into a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Mingze Xu , Mingfei Gao , Shiyu Li , Jiasen Lu , Zhe Gan , Zhengfeng Lai , Meng Cao , Kai Kang , Yinfei Yang , Afshin Dehghan

Large Vision-Language Models (LVLMs) excel in visual understanding and reasoning, but the excessive visual tokens lead to high inference costs. Although recent token reduction methods mitigate this issue, they mainly target single-turn…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Yi Wang , Haofei Zhang , Qihan Huang , Anda Cao , Gongfan Fang , Wei Wang , Xuan Jin , Jie Song , Mingli Song , Xinchao Wang

While Large Vision-Language Models (LVLMs) have achieved substantial progress in video understanding, their application to long video reasoning is hindered by uniform frame sampling and static textual reasoning, which are inefficient and…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Zefeng He , Xiaoye Qu , Yafu Li , Siyuan Huang , Daizong Liu , Yu Cheng

Video-language models (VLMs) face rapid inference costs as visual token counts scale with video length. For example, 32 frames at $448{\times}448$ resolution already yield >8,000 visual tokens in Qwen3-VL, making LLM prefill the dominant…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Simin Huo , Ning LI

Large Vision-Language Models (LVLMs) generate contextually relevant responses by jointly interpreting visual and textual inputs. However, our finding reveals they often mistakenly perceive text inputs lacking visual evidence as being part…

Computer Vision and Pattern Recognition · Computer Science 2025-09-08 Sohee Kim , Soohyun Ryu , Joonhyung Park , Eunho Yang

Existing Multimodal Large Language Models (MLLMs) follow the paradigm that perceives visual information by aligning visual features with the input space of Large Language Models (LLMs), and concatenating visual tokens with text tokens to…

Computer Vision and Pattern Recognition · Computer Science 2024-05-31 Feipeng Ma , Hongwei Xue , Guangting Wang , Yizhou Zhou , Fengyun Rao , Shilin Yan , Yueyi Zhang , Siying Wu , Mike Zheng Shou , Xiaoyan Sun

Reading dense text and locating objects within images are fundamental abilities for Large Vision-Language Models (LVLMs) tasked with advanced jobs. Previous LVLMs, including superior proprietary models like GPT-4o, have struggled to excel…

Computer Vision and Pattern Recognition · Computer Science 2024-10-08 Ya-Qi Yu , Minghui Liao , Jiwen Zhang , Jihao Wu

This paper introduces an efficient Vision-Language Model (VLM) pipeline specifically optimized for deployment on embedded devices, such as those used in robotics and autonomous driving. The pipeline significantly reduces the computational…

Machine Learning · Computer Science 2025-11-04 Jin Huang , Yuchao Jin , Le An , Josh Park

Despite interpretability work analyzing VIT encoders and transformer activations, we don't yet understand why Multimodal Language Models (MLMs) struggle on perception-heavy tasks. We offer an under-studied perspective by examining how…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Benlin Liu , Amita Kamath , Madeleine Grunde-McLaughlin , Winson Han , Ranjay Krishna

Large Vision-Language Models (LVLMs) have experienced significant advancements in recent years. However, their performance still falls short in tasks requiring deep visual perception, such as identifying subtle differences between images. A…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Qingguo Hu , Ante Wang , Jia Song , Delai Qiu , Qingsong Liu , Jinsong Su

Video Large Language Models (VideoLLMs) have demonstrated impressive capabilities in video understanding, yet the massive number of input video tokens incurs a significant computational burden for deployment. Existing methods mainly prune…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Yansong Guo , Chaoyang Zhu , Jiayi Ji , Jianghang Lin , Liujuan Cao

The practical application of Multimodal Large Language Models (MLLMs) to Video Question Answering (Video-QA) is severely hindered by the high token cost of processing numerous video frames. While keyframe selection is the dominant strategy…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Shaoguang Wang , Weiyu Guo , Ziyang Chen , Yijie Xu , Xuming Hu , Hui Xiong

Training-free video understanding leverages the strong image comprehension capabilities of pre-trained vision language models (VLMs) by treating a video as a sequence of static frames, thus obviating the need for costly video-specific…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Baiyang Song , Jun Peng , Yuxin Zhang , Guangyao Chen , Feidiao Yang , Jianyuan Guo

Building models that comprehends videos and responds specific user instructions is a practical and challenging topic, as it requires mastery of both vision understanding and knowledge reasoning. Compared to language and image modalities,…

Computer Vision and Pattern Recognition · Computer Science 2024-04-30 Ji Qi , Kaixuan Ji , Jifan Yu , Duokang Wang , Bin Xu , Lei Hou , Juanzi Li

The exponential growth of Large Multimodal Models (LMMs) has driven advancements in cross-modal reasoning but at significant computational costs. In this work, we focus on visual language models. We highlight the redundancy and inefficiency…

Computer Vision and Pattern Recognition · Computer Science 2025-04-28 Yasmine Omri , Parth Shroff , Thierry Tambe

To effectively reduce the visual tokens in Visual Large Language Models (VLLMs), we propose a novel approach called Window Token Concatenation (WiCo). Specifically, we employ a sliding window to concatenate spatially adjacent visual tokens.…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Yifan Li , Wentao Bao , Botao Ye , Zhen Tan , Tianlong Chen , Huan Liu , Yu Kong

Despite the impressive advancements of Large Vision-Language Models (LVLMs), existing approaches suffer from a fundamental bottleneck: inefficient visual-language integration. Current methods either disrupt the model's inherent structure or…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Tongtian Yue , Longteng Guo , Yepeng Tang , Zijia Zhao , Xinxin Zhu , Hua Huang , Jing Liu

Video-Language Models (VLMs), powered by the advancements in Large Language Models (LLMs), are charting new frontiers in video understanding. A pivotal challenge is the development of an efficient method to encapsulate video content into a…

Computer Vision and Pattern Recognition · Computer Science 2024-02-21 Jiaqi Xu , Cuiling Lan , Wenxuan Xie , Xuejin Chen , Yan Lu

Multimodal large language models (LLMs) have made rapid progress in visual understanding, yet their extension from images to videos often reduces to a naive concatenation of frame tokens. In this work, we investigate what video finetuning…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Ruiqi Yang , Tian Yun , Zihan Wang , Ellie Pavlick