Qvad: A question-centric agentic framework for efficient and training-free video anomaly detection

Bekit, Lokman, Hamza Karim, Nghia T Nguyen, and Yasin Yilmaz. 2026. “Qvad: A Question-Centric Agentic Framework for Efficient and Training-Free Video Anomaly Detection”. ArXiv Preprint ArXiv:2604.03040.