AINeutralarXiv – CS AI · Mar 96/10
🧠
Probing Visual Concepts in Lightweight Vision-Language Models for Automated Driving
Researchers analyzed Vision-Language Models (VLMs) used in automated driving to understand why they fail on simple visual tasks. They identified two failure modes: perceptual failure where visual information isn't encoded, and cognitive failure where information is present but not properly aligned with language semantics.