Time-series anomaly detection (TSAD) is critical in domains such as industrial monitoring, healthcare, and cybersecurity, but it remains challenging due to rare and heterogeneous anomalies and the scarcity of labelled data. This scarcity makes unsupervised approaches predominant, yet existing methods often rely on reconstruction or forecasting, which struggle with complex data, or on embedding-based approaches that require domain-specific anomaly synthesis and fixed distance metrics. We propose ASTER, a framework that generates pseudo-anomalies directly in the latent space, avoiding handcrafted anomaly injections and the need for domain expertise. A latent-space decoder produces tailored pseudo-anomalies to train a Transformer-based anomaly classifier, while a pre-trained LLM enriches the temporal and contextual representations of this space. Experiments on three benchmark datasets show that ASTER achieves state-of-the-art performance and sets a new standard for LLM-based TSAD.
@article{arxiv.2604.13924,
title = {ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection},
author = {Romain Hermary and Samet Hicsonmez and Dan Pineau and Abd El Rahman Shabayek and Djamila Aouada},
journal= {arXiv preprint arXiv:2604.13924},
year = {2026}
}