AI RESEARCH
Can VLMs Unlock Semantic Anomaly Detection? A Framework for Structured Reasoning
arXiv CS.CV
•
ArXi:2510.18034v2 Announce Type: replace Autonomous driving systems remain critically vulnerable to the long-tail of rare, out-of-distribution semantic anomalies. While VLMs have emerged as promising tools for perception, their application in anomaly detection remains largely restricted to prompting