Architecture, Data, and Scale Don't Explain Universality in Vision Models

martin_hebart · x · 2026-09-25

Thread follow-up: universality was not explained by differences in architecture, training data, training objective, model size, or ImageNet performance.

Related event: Hebart team: Universality in model representations is an emergent, human-aligned property(5 posts)→

Original post →

More from Research

Research channel →