3 papers
cs.CV2026
Representation--Behavior Alignment for Explainable Weakly-Supervised Video Anomaly Detection
Chao Huang, Pengfei Wei, Kaige Li +4
Multimodal Large Language Models (MLLMs) provide a natural way to make video anomaly detection more explainable. However, their final decisions do not always fully use the discrimi…
cs.CV2026
VFAD: Variational Semantic Prompting Meets Frequency-Adaptive Representation Learning for Zero-Shot Anomaly Detection
Peng Chen, Kaige Li, Wei Wang +5
Zero-shot anomaly detection (ZSAD) aims to detect and localize anomalies in unseen categories without access to target-specific training data. Although recent CLIP-based methods ha…
cs.AI2026
AdvNav: Behavior-Guided Black-Box Adversarial Attacks on Vision-Language Navigation
Chenyang Li, Kaige Li, Zeyu Jiang +1
Despite progress in Embodied AI, Vision-and-Language Navigation systems remain vulnerable to adversarial visual disturbances. Most existing methods rely on white-box access to targ…