AI RESEARCH
Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models
arXiv CS.CV
•
ArXi:2604.07802v1 Announce Type: new Large-scale vision-language models (VLMs) exhibit remarkable zero-shot capabilities, yet the internal mechanisms driving their anomaly detection (AD) performance remain poorly understood. Current methods predominantly treat VLMs as black-box feature extractors, assuming that anomaly-specific knowledge must be acquired through external adapters or memory banks. In this paper, we challenge this assumption by arguing that anomaly knowledge is intrinsically embedded within pre-trained models but remains latent and under-activated.