# Visual Interestingness Decoded: How GPT-4o Mirrors Human Interests

arXiv: https://arxiv.org/abs/2510.13316 · HTML: https://mlsanity.com/paper/2510.13316/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 15 Oct 2025.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding](https://mlsanity.com/paper/2412.10302/) (2024)
- [A Survey on Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2402.13116/) (2024)
- [What does a platypus look like? Generating customized prompts for zero-shot image classification](https://mlsanity.com/paper/2209.03320/) (2022)
- [Towards Understanding Grokking: An Effective Theory of Representation Learning](https://mlsanity.com/paper/2205.10343/) (2022)
- [GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation](https://mlsanity.com/paper/2401.04092/) (2024)
- [DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation](https://mlsanity.com/paper/2406.16855/) (2024)
- [Towards Open-ended Visual Quality Comparison](https://mlsanity.com/paper/2402.16641/) (2024)
- [VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining](https://mlsanity.com/paper/2303.14302/) (2023)
- [Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero](https://mlsanity.com/paper/2310.16410/) (2023)
- [Can GPTs Evaluate Graphic Design Based on Design Principles?](https://mlsanity.com/paper/2410.08885/) (2024)
- [Embracing New Techniques in Deep Learning for Estimating Image Memorability](https://mlsanity.com/paper/2105.10598/) (2021)
- [Understanding Image Virality](https://mlsanity.com/paper/1503.02318/) (2015)
- [Commonly Interesting Images](https://mlsanity.com/paper/2409.16736/) (2024)
- [An Empirical Analysis of GPT-4V's Performance on Fashion Aesthetic Evaluation](https://mlsanity.com/paper/2410.23730/) (2024)
- [AID-AppEAL: Automatic Image Dataset and Algorithm for Content Appeal Enhancement and Assessment Labeling](https://mlsanity.com/paper/2407.05546/) (2024)

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

- [Neuroscience-Inspired Analyses of Visual Interestingness in Multimodal Transformers](https://mlsanity.com/paper/2605.08188/) (2026)

## Abstract (arXiv)

Our daily life is highly influenced by what we consume and see. Attracting and holding one's attention -- the definition of (visual) interestingness -- is essential. The rise of Large Multimodal Models (LMMs) trained on large-scale visual and textual data has demonstrated impressive capabilities. We explore these models' potential to understand to what extent the concepts of visual interestingness are captured and examine the alignment between human assessments and GPT-4o's, a leading LMM, predictions through comparative analysis. Our studies reveal partial alignment between humans and GPT-4o. It already captures the concept as best compared to state-of-the-art methods. Hence, this allows for the effective labeling of image pairs according to their (commonly) interestingness, which are used as training data to distill the knowledge into a learning-to-rank model. The insights pave the way for a deeper understanding of human interest.