This document discusses anomaly detection using Auxiliary VAE (ADGM) and Ladder VAE (LVAE) models. It summarizes the VAE, ADGM, and LVAE models and how they are used for anomaly detection. It then evaluates the models on the NAB dataset, finding that while the models can detect anomalies based on reconstruction error on MNIST with noise, they have difficulty detecting anomalies in the NAB time-series data.