2 papers
cs.LG2026
LightGTS-Cov: Covariate-Enhanced Time Series Forecasting
Yong Shang, Zhipeng Yao, Ning Jin +3
Time series foundation models are typically pre-trained on large, multi-source datasets; however, they often ignore exogenous covariates or incorporate them via simple concatenatio…
cs.LG2025
CrossAD: Time Series Anomaly Detection with Cross-scale Associations and Cross-window Modeling
Beibu Li, Qichao Shentu, Yang Shu +5
Time series anomaly detection plays a crucial role in a wide range of real-world applications. Given that time series data can exhibit different patterns at different sampling gran…