# How AI Experiences Art: Emergent Aesthetic Structure in a Self-Supervised Multimodal Embedding Space

arXiv: https://arxiv.org/abs/2608.27121 · HTML: https://mlsanity.com/paper/2608.27121/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 27 Aug 2026.

## Builds on (most cited first, 8 of 8)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [SCAN: Learning to Classify Images without Labels](https://mlsanity.com/paper/2005.12320/) (2020)
- [Revisiting Image Aesthetic Assessment via Self-Supervised Feature Learning](https://mlsanity.com/paper/1911.11419/) (2019)

## Abstract (arXiv)

Aesthetics are an important part of the symbolism of artistic works. Although subjective, humans categorize art based on the emotion evoked regardless of modality. What remains under-explored is how AI models form their own aesthetic categorization of human-produced media without explicit labels or cross-modal supervision. We present a self-supervised framework that projects four modalities (text, audio, image and video) into a shared 256-dimensional embedding space and applies iterative clustering to discover aesthetic structure. We discuss the divergence between AI-generated cluster assignments and human affective register labels on a weakly supervised multimodal dataset. This work has applications in understanding how AI structures cross-modal similarity, organizing heterogeneous media collections for Retrieval-Augmented Generation (RAG), and automated data labeling.