Untrained Neural Networks Hit 86.4% AUROC on ADBench Anomaly Detection

ideal-lab-sejong · hf · 2026-11-20

A paper from ideal-lab (Sejong University) proposes PRISM, which uses fixed random nonlinear features plus Mahalanobis scoring for anomaly detection — no weight optimization or pretrained representations.

Original post →

More from Research

Research channel →