{"ID":2836823,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.20056","arxiv_id":"2511.20056","title":"Online-PVLM: Advancing Personalized VLMs with Online Concept Learning","abstract":"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.","short_abstract":"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 adaptat...","url_abs":"https://arxiv.org/abs/2511.20056","url_pdf":"https://arxiv.org/pdf/2511.20056v2","authors":"[\"Huiyu Bai\",\"Runze Wang\",\"Zhuoyun Du\",\"Yiyang Zhao\",\"Fengji Zhang\",\"Haoyu Chen\",\"Xiaoyong Zhu\",\"Bo Zheng\",\"Xuejiao Zhao\"]","published":"2025-11-25T08:25:30Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Language Model\"]","has_code":false}