Princeton study: diffusion models barely extrapolate basic visual skills, ~50% on counts

NielsRogge · x · 2026-11-23

Princeton researchers Amish Sethi, Boya Zeng, Wenhao Chai, and Zhuang Liu released "Do Diffusion Models Learn to Generalize Basic Visual Skills?" (arXiv:2611.22427), introducing the Visual Generative Lab (VGL), a controlled framework that trains diffusion models from scratch on rule-generated synthetic data to precisely measure generalization of basic visual skills — size, position, rotation, count, color, shape — something FID/IS metrics and prompt-following benchmarks can't reveal.

Key findings:

Code and data-generation scripts are open-sourced on GitHub.

Original post →

More from Multimodal

Multimodal channel →