Online-PVLM: Advancing Personalized VLMs with Online Concept Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bai, Huiyu, Wang, Runze, Du, Zhuoyun, Zhao, Yiyang, Zhang, Fengji, Chen, Haoyu, Zhu, Xiaoyong, Zheng, Bo, Zhao, Xuejiao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912772373086208
author Bai, Huiyu
Wang, Runze
Du, Zhuoyun
Zhao, Yiyang
Zhang, Fengji
Chen, Haoyu
Zhu, Xiaoyong
Zheng, Bo
Zhao, Xuejiao
author_facet Bai, Huiyu
Wang, Runze
Du, Zhuoyun
Zhao, Yiyang
Zhang, Fengji
Chen, Haoyu
Zhu, Xiaoyong
Zheng, Bo
Zhao, Xuejiao
contents Personalized Visual Language Models (VLMs) are gaining increasing attention for their formidable ability in user-specific concepts aligned interactions (e.g., identifying a user's bike). Existing methods typically require the learning of separate embeddings for each new concept, which fails to support real-time adaptation during testing. This limitation becomes particularly pronounced in large-scale scenarios, where efficient retrieval of concept embeddings is not achievable. To alleviate this gap, we propose Online-PVLM, a framework for online concept learning by leveraging hyperbolic representations. Our approach makes a train-free paradigm for concept embeddings generation at test time, making the use of personalized VLMs both scalable and efficient. In addition, we develop OP-Eval, a comprehensive and large-scale benchmark comprising 1,292 concepts and over 30K high-quality instances with diverse question types, designed to rigorously assess online concept learning in realistic scenarios. Extensive experiments demonstrate the state-of-the-art performance of our proposed framework. Our source code and dataset will be made available.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20056
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Online-PVLM: Advancing Personalized VLMs with Online Concept Learning
Bai, Huiyu
Wang, Runze
Du, Zhuoyun
Zhao, Yiyang
Zhang, Fengji
Chen, Haoyu
Zhu, Xiaoyong
Zheng, Bo
Zhao, Xuejiao
Computation and Language
Personalized Visual Language Models (VLMs) are gaining increasing attention for their formidable ability in user-specific concepts aligned interactions (e.g., identifying a user's bike). Existing methods typically require the learning of separate embeddings for each new concept, which fails to support real-time adaptation during testing. This limitation becomes particularly pronounced in large-scale scenarios, where efficient retrieval of concept embeddings is not achievable. To alleviate this gap, we propose Online-PVLM, a framework for online concept learning by leveraging hyperbolic representations. Our approach makes a train-free paradigm for concept embeddings generation at test time, making the use of personalized VLMs both scalable and efficient. In addition, we develop OP-Eval, a comprehensive and large-scale benchmark comprising 1,292 concepts and over 30K high-quality instances with diverse question types, designed to rigorously assess online concept learning in realistic scenarios. Extensive experiments demonstrate the state-of-the-art performance of our proposed framework. Our source code and dataset will be made available.
title Online-PVLM: Advancing Personalized VLMs with Online Concept Learning
topic Computation and Language
url https://arxiv.org/abs/2511.20056