Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Miao, Zhang, Ruixiao, Shi, Jianxin, Wang, Hengzhi, Fang, Hao, Liu, Jiangchuan
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2603.00126
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912931741958144
author Zhang, Miao
Zhang, Ruixiao
Shi, Jianxin
Wang, Hengzhi
Fang, Hao
Liu, Jiangchuan
author_facet Zhang, Miao
Zhang, Ruixiao
Shi, Jianxin
Wang, Hengzhi
Fang, Hao
Liu, Jiangchuan
contents Video-language models (VLMs) are reshaping video querying services, bringing unified solutions to complex perception and reasoning tasks. However, deploying large VLMs in real-world systems remains challenging due to their high resource demands, and remote-based deployment often results in unacceptable response delays. Although small, locally deployable VLMs offer faster responses, they unavoidably fall short in accuracy. To reconcile this trade-off, we propose QuickGrasp, a responsive, quality of service (QoS)-aware system that bridges this gap through a local-first architecture with on-demand edge augmentation. Built upon the highly modular architecture of VLMs, QuickGrasp shares the vision representation across model variants to avoid redundant computation. To maximize system-wide efficiency, QuickGrasp introduces three key designs: accelerated video tokenization, query-adaptive edge augmentation, and delay-aware, accuracy-preserving vision token density configuration. We implement a prototype of QuickGrasp and evaluate it across multiple video understanding benchmarks. The results show that QuickGrasp matches the accuracy of large VLMs while achieving up to a 12.8x reduction in response delay. QuickGrasp represents a key advancement toward building responsive video querying services for open-world understanding that fully leverage the capabilities of VLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2603_00126
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle QuickGrasp: Responsive Video-Language Querying Service via Accelerated Tokenization and Edge-Augmented Inference
Zhang, Miao
Zhang, Ruixiao
Shi, Jianxin
Wang, Hengzhi
Fang, Hao
Liu, Jiangchuan
Computer Vision and Pattern Recognition
Artificial Intelligence
Information Retrieval
Multimedia
Performance
Systems and Control
Video-language models (VLMs) are reshaping video querying services, bringing unified solutions to complex perception and reasoning tasks. However, deploying large VLMs in real-world systems remains challenging due to their high resource demands, and remote-based deployment often results in unacceptable response delays. Although small, locally deployable VLMs offer faster responses, they unavoidably fall short in accuracy. To reconcile this trade-off, we propose QuickGrasp, a responsive, quality of service (QoS)-aware system that bridges this gap through a local-first architecture with on-demand edge augmentation. Built upon the highly modular architecture of VLMs, QuickGrasp shares the vision representation across model variants to avoid redundant computation. To maximize system-wide efficiency, QuickGrasp introduces three key designs: accelerated video tokenization, query-adaptive edge augmentation, and delay-aware, accuracy-preserving vision token density configuration. We implement a prototype of QuickGrasp and evaluate it across multiple video understanding benchmarks. The results show that QuickGrasp matches the accuracy of large VLMs while achieving up to a 12.8x reduction in response delay. QuickGrasp represents a key advancement toward building responsive video querying services for open-world understanding that fully leverage the capabilities of VLMs.
title QuickGrasp: Responsive Video-Language Querying Service via Accelerated Tokenization and Edge-Augmented Inference
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Information Retrieval
Multimedia
Performance
Systems and Control
url https://arxiv.org/abs/2603.00126