SOURCE-LINKED INTELLIGENCE

Do Vision-Language Models Agree on the Affective Qualities of Shape? A Cross-Model Audit for Generative Design Interfaces

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Generative design interfaces increasingly expose semantic controls that let users steer output with concepts such as "more elegant" or "more minimalist," typically encoded by a vision-language model (VLM). A practical question is whether state-of-the-art VLMs represent objects consistently in terms of the same concept. We audit 6 VLMs by ranking untextured 3D objects along Kansei adjective pairs, where Kansei describes affective impressions of product form, with each axis defined as the difference between the text representations of its two poles. Geometric pairs serve as positive controls, an

Read original source ↗ Open in workspace

recordType

paper

region

Global