News
Paper accepted to ICML 2026: Towards foundation models for zero-shot time series anomaly detection: Leveraging synthetic data and relative context discrepancy
arXiv linkPreprint posted: VETime: Vision Enhanced Zero-Shot Time Series Anomaly Detection
arXiv linkPreprint posted: Towards foundation models for zero-shot time series anomaly detection: Leveraging synthetic data and relative context discrepancy
arXiv linkPreprint posted: AXIS: Explainable Time Series Anomaly Detection with Large Language Models
arXiv linkPaper accepted to NIPS 2025: TraffiDent: A Dataset for Understanding the Interplay Between Traffic Dynamics and Incidents
arXiv linkPreprint posted: Tensor State Space-based Dynamic Multilayer Network Modeling
arXiv linkPreprint posted: CICADA: Cross-Domain Interpretable Coding for Anomaly Detection and Adaptation in Multivariate Time Series
arXiv link