SOURCE-LINKED INTELLIGENCE

Diffusion Models and Concept Formation

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Humans organize knowledge into a taxonomy of concepts with nested levels of abstraction and a \emph{basic level} at which people recognize and name objects with the least cognitive effort. Cobweb is a classic cognitive account of this ability, an incremental learner that builds a probabilistic concept hierarchy by maximizing category utility. We argue that diffusion models, although designed for image synthesis, implicitly perform the same computation. The noisy marginals of a diffusion model are Gaussian smoothings of the data distribution, and the modes of these marginals form a hierarchy th

Read original source ↗ Open in workspace

recordType

paper

region

Global