# Personalized Image Aesthetic Assessment via Preference-rich Sample Mining and Cohort Merging

arXiv: https://arxiv.org/abs/2607.15752 · HTML: https://mlsanity.com/paper/2607.15752/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 55 references that are in the map.
- First posted on arXiv 17 Jul 2026.

## Builds on (most cited first, 21 of 21)

- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities](https://mlsanity.com/paper/2408.07666/) (2024)
- [Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution](https://mlsanity.com/paper/2501.11561/) (2025)
- [Photo Aesthetics Ranking Network with Attributes and Content Adaptation](https://mlsanity.com/paper/1606.01621/) (2016)
- [Parameter Efficient Multi-task Model Fusion with Partial Linearization](https://mlsanity.com/paper/2310.04742/) (2023)
- [AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception](https://mlsanity.com/paper/2401.08276/) (2024)
- [Personalized Image Aesthetics Assessment with Rich Attributes](https://mlsanity.com/paper/2203.16754/) (2022)
- [AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception](https://mlsanity.com/paper/2404.09624/) (2024)
- [Image Aesthetic Assessment: An Experimental Survey](https://mlsanity.com/paper/1610.00838/) (2016)
- [Multimodal Pretraining, Adaptation, and Generation for Recommendation: A Survey](https://mlsanity.com/paper/2404.00621/) (2024)
- [Tailored Visions: Enhancing Text-to-Image Generation with Personalized Prompt Rewriting](https://mlsanity.com/paper/2310.08129/) (2023)
- [Personalized Image Generation with Deep Generative Models: A Decade Survey](https://mlsanity.com/paper/2502.13081/) (2025)
- [LAPIS: A novel dataset for personalized image aesthetic assessment](https://mlsanity.com/paper/2504.07670/) (2025)
- [Fine-grained Image Quality Assessment for Perceptual Image Restoration](https://mlsanity.com/paper/2508.14475/) (2025)
- [Scaling Up Personalized Image Aesthetic Assessment via Task Vector Customization](https://mlsanity.com/paper/2407.07176/) (2024)
- [USAR: an Interactive User-specific Aesthetic Ranking Framework for Images](https://mlsanity.com/paper/1805.01091/) (2018)
- [Language-Guided Visual Perception Disentanglement for Image Quality Assessment and Conditional Image Generation](https://mlsanity.com/paper/2503.02206/) (2025)
- [LongT2IBench: A Benchmark for Evaluating Long Text-to-Image Generation with Graph-structured Annotations](https://mlsanity.com/paper/2512.09271/) (2025)
- [On the Role of Individual Differences in Current Approaches to Computational Image Aesthetics](https://mlsanity.com/paper/2502.20518/) (2025)

## Built on by (most cited first, 1 of 1)

- [Learning Heterogeneous Preferences](https://mlsanity.com/paper/2609.17847/) (2026)

## Abstract (arXiv)

Personalized Image Aesthetic Assessment (PIAA) aims to predict aesthetic ratings of images that vary across individuals. The aesthetic preferences manifest to different extents across distinct visual stimuli and exhibit cohort-specific patterns. Motivated by the above fact, this paper presents a Multimodal Large Language Model (MLLM)-based approach, which models individual aesthetic preferences by Preference-Rich sample mining and Aesthetically-resonant Cohort merging (PRAC). Specifically, PRAC first identifies preference-rich samples by analyzing both Collective Controversy and Personalized Deviation of images, maximizing the utility of limited user data. Based upon the preference-rich samples, cross-user preference similarities are measured by comparing preference embeddings. Then, a cohort-based model merging strategy, is proposed by aggregating preference patterns from aesthetically-resonant users, which further enhances the personalization for the target individual. Extensive experiments and comparisons on four benchmark PIAA databases demonstrate the superiority of the proposed PRAC model over the state-of-the-arts. The code and model will be public at https://github.com/yzc-ippl/PRAC.