Research
How AI Experiences Art: Emergent Aesthetic Structure in a Self-Supervised Multimodal Embedding Space
arXiv:2608.27121v1 Announce Type: cross Abstract: Aesthetics are an important part of the symbolism of artistic works. Although subjective, humans categorize art based on the emotion evoked regardless
arXiv:2608.27121v1 Announce Type: cross Abstract: 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.
Related
- Walkable to Whom? Capturing Subjective Variability in Walkability Perception Using Multimodal Deep Learning
- Navigating the Emotion Tree: Hierarchical Hyperbolic RAG for Multimodal Emotion Recognition
- Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception
- Geometric Analysis of Self-Supervised Vision Representations for Semantic Image Retrieval
Source: arXiv cs.CV | 2026-08-28