Beauty is in the ELBO of the Beholder: A Variational Account of Processing Fluency in Face Perception
Why our brains find symmetrical, average faces more beautiful
Faces we find attractive are easier for our brains to process — they match statistical patterns our visual system encounters most often. Researchers trained artificial neural networks on face images without any beauty labels, then checked whether the networks' internal representations matched human attractiveness ratings. Across multiple datasets, faces rated as attractive aligned with directions in the network's latent space that required the least computational effort to encode, and these "beauty directions" emerged consistently even when networks were retrained from scratch.
This work bridges neuroscience and artificial intelligence by showing that aesthetic pleasure may be rooted in processing efficiency rather than arbitrary cultural preferences. Understanding what makes faces attractive has applications in facial recognition systems, cosmetic surgery planning, and media design — and suggests that beauty judgments might be partly universal rather than entirely learned.