Enhancing Zero-shot Personalized Image Aesthetics Assessment with Profile-aware Multimodal LLM
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908977853366272 |
|---|---|
| author | Wang, Chun Wei, Chenfeng Liu, Chenyang Deng, Weihong |
| author_facet | Wang, Chun Wei, Chenfeng Liu, Chenyang Deng, Weihong |
| contents | Personalized image aesthetics assessment (PIAA) aims to predict an individual user's subjective rating of an image, which requires modeling user-specific aesthetic preferences. Existing methods rely on historical user ratings for this modeling and therefore struggle when such data are unavailable. We address this zero-shot setting by using user profiles as contextual signals for personalization and adopting a profile-based personalization paradigm. We introduce P-MLLM, a profile-aware multimodal LLM that augments a frozen LLM with selective fusion modules for controlled visual integration. These modules selectively integrate visual information into the model's evolving hidden states during profile-conditioned reasoning, allowing visual information to be incorporated in a profile-aware manner. Experiments on recent PIAA benchmarks show that P-MLLM achieves competitive zero-shot performance and remains effective even with coarse profile information, highlighting the potential of profile-based personalization for zero-shot PIAA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_17233 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Enhancing Zero-shot Personalized Image Aesthetics Assessment with Profile-aware Multimodal LLM Wang, Chun Wei, Chenfeng Liu, Chenyang Deng, Weihong Computer Vision and Pattern Recognition Artificial Intelligence Personalized image aesthetics assessment (PIAA) aims to predict an individual user's subjective rating of an image, which requires modeling user-specific aesthetic preferences. Existing methods rely on historical user ratings for this modeling and therefore struggle when such data are unavailable. We address this zero-shot setting by using user profiles as contextual signals for personalization and adopting a profile-based personalization paradigm. We introduce P-MLLM, a profile-aware multimodal LLM that augments a frozen LLM with selective fusion modules for controlled visual integration. These modules selectively integrate visual information into the model's evolving hidden states during profile-conditioned reasoning, allowing visual information to be incorporated in a profile-aware manner. Experiments on recent PIAA benchmarks show that P-MLLM achieves competitive zero-shot performance and remains effective even with coarse profile information, highlighting the potential of profile-based personalization for zero-shot PIAA. |
| title | Enhancing Zero-shot Personalized Image Aesthetics Assessment with Profile-aware Multimodal LLM |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2604.17233 |