Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Sihan, Ji, Huitong, Lu, Shaolin, Chen, Jiayi, Xu, Binxiao, Lu, Ming, Zhang, Yuanxing, Dong, Wenhui, Zhang, Wentao
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2508.07260
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911100636758016
author Yang, Sihan
Ji, Huitong
Lu, Shaolin
Chen, Jiayi
Xu, Binxiao
Lu, Ming
Zhang, Yuanxing
Dong, Wenhui
Zhang, Wentao
author_facet Yang, Sihan
Ji, Huitong
Lu, Shaolin
Chen, Jiayi
Xu, Binxiao
Lu, Ming
Zhang, Yuanxing
Dong, Wenhui
Zhang, Wentao
contents Personalizing Vision-Language Models (VLMs) to transform them into daily assistants has emerged as a trending research direction. However, leading companies like OpenAI continue to increase model size and develop complex designs such as the chain of thought (CoT). While large VLMs are proficient in complex multi-modal understanding, their high training costs and limited access via paid APIs restrict direct personalization. Conversely, small VLMs are easily personalized and freely available, but they lack sufficient reasoning capabilities. Inspired by this, we propose a novel collaborative framework named Small-Large Collaboration (SLC) for large VLM personalization, where the small VLM is responsible for generating personalized information, while the large model integrates this personalized information to deliver accurate responses. To effectively incorporate personalized information, we develop a test-time reflection strategy, preventing the potential hallucination of the small VLM. Since SLC only needs to train a meta personalized small VLM for the large VLMs, the overall process is training-efficient. To the best of our knowledge, this is the first training-efficient framework that supports both open-source and closed-source large VLMs, enabling broader real-world personalized applications. We conduct thorough experiments across various benchmarks and large VLMs to demonstrate the effectiveness of the proposed SLC framework. The code will be released at https://github.com/Hhankyangg/SLC.
format Preprint
id arxiv_https___arxiv_org_abs_2508_07260
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Small-Large Collaboration: Training-efficient Concept Personalization for Large VLM using a Meta Personalized Small VLM
Yang, Sihan
Ji, Huitong
Lu, Shaolin
Chen, Jiayi
Xu, Binxiao
Lu, Ming
Zhang, Yuanxing
Dong, Wenhui
Zhang, Wentao
Computer Vision and Pattern Recognition
Personalizing Vision-Language Models (VLMs) to transform them into daily assistants has emerged as a trending research direction. However, leading companies like OpenAI continue to increase model size and develop complex designs such as the chain of thought (CoT). While large VLMs are proficient in complex multi-modal understanding, their high training costs and limited access via paid APIs restrict direct personalization. Conversely, small VLMs are easily personalized and freely available, but they lack sufficient reasoning capabilities. Inspired by this, we propose a novel collaborative framework named Small-Large Collaboration (SLC) for large VLM personalization, where the small VLM is responsible for generating personalized information, while the large model integrates this personalized information to deliver accurate responses. To effectively incorporate personalized information, we develop a test-time reflection strategy, preventing the potential hallucination of the small VLM. Since SLC only needs to train a meta personalized small VLM for the large VLMs, the overall process is training-efficient. To the best of our knowledge, this is the first training-efficient framework that supports both open-source and closed-source large VLMs, enabling broader real-world personalized applications. We conduct thorough experiments across various benchmarks and large VLMs to demonstrate the effectiveness of the proposed SLC framework. The code will be released at https://github.com/Hhankyangg/SLC.
title Small-Large Collaboration: Training-efficient Concept Personalization for Large VLM using a Meta Personalized Small VLM
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.07260