SOURCE-LINKED INTELLIGENCE

Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Although text-to-image diffusion models generally exhibit strong prompt-following ability, we identify a persistent and previously underexplored failure pattern in which a small subset of prompts differing only in the object consistently fails to realize the same target concept under identical generation settings. We term this phenomenon object-dependent concept brittleness. Such cases suggest systematic internal blind spots rather than random sampling noise. In this paper, we present an interpretability-oriented framework to audit and minimally correct these failures. Our key idea is to analy

Read original source ↗ Open in workspace

recordType: paper
region: Global

Evidence & attribution

arXiv · AI, language, vision and robotics · 2026-09-09T09:07:40.000Z

First collected: 2026-09-20T19:32:24.350Z. This is not the publication date.