Learning universal time series representations applicable to various types of downstream
tasks is challenging but valuable in real applications. Recently, researchers have attempted …

Although pre-trained transformers and reprogrammed text-based LLMs have shown strong
performance on time series tasks, the best-performing architectures vary widely across …

Label-efficient time series representation learning, which aims to learn effective
representations with limited labeled data, is crucial for deploying deep learning models in …

Artificial Intelligence (AI) methods are powerful tools for various domains, including critical
fields such as avionics, where certification is required to achieve and maintain an …

In the era of big data and Artificial Intelligence, an emerging paradigm is to utilize contrastive
self-supervised learning to model large-scale heterogeneous data. Many existing foundation …

Time-series data exists in every corner of real-world systems and services, ranging from
satellites in the sky to wearable devices on human bodies. Learning representations by …

Multivariate time series (MTS) forecasting is crucial in many real-world applications. To
achieve accurate MTS forecasting, it is essential to simultaneously consider both intra-and …

Abstract Time-Series Classification (TSC) has gained substantial importance in applications
such as healthcare, finance, manufacturing, and human activity recognition. Training and …

In recent years, Contrastive Learning (CL) has become a predominant representation
learning paradigm for time series. Most existing methods manually build specific CL …

Monitoring bearing failures in production equipment can effectively prevent finished product
quality issues and unplanned factory downtime, thereby reducing supply chain uncertainties …