3 papers
cs.CV2025
HeadHunt-VAD: Hunting Robust Anomaly-Sensitive Heads in MLLM for Tuning-Free Video Anomaly Detection
Zhaolin Cai, Fan Li, Ziwei Zheng +2
Video Anomaly Detection (VAD) aims to locate events that deviate from normal patterns in videos. Traditional approaches often rely on extensive labeled data and incur high computat…
cs.CV2025
HiProbe-VAD: Video Anomaly Detection via Hidden States Probing in Tuning-Free Multimodal LLMs
Zhaolin Cai, Fan Li, Ziwei Zheng +1
Video Anomaly Detection (VAD) aims to identify and locate deviations from normal patterns in video sequences. Traditional methods often struggle with substantial computational dema…
cs.LG2025
Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models
Ziwei Zheng, Junyao Zhao, Le Yang +2
With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-o…