Deep Neural Networks (DNNs) trained on one dataset (source domain) do not perform well
on another set of data (target domain), which is different but has similar properties as the …

Real-world time series are characterized by intrinsic non-stationarity that poses a principal
challenge for deep forecasting models. While previous models suffer from complicated …

Unsupervised domain adaptation (UDA) enables the transfer of models trained on source
domains to unlabeled target domains. However, transferring complex time series models …

Data-driven autonomous driving motion generation tasks are frequently impacted by the
limitations of dataset size and the domain gap between datasets, which precludes their …

We introduce Chronos, a simple yet effective framework for pretrained probabilistic time
series models. Chronos tokenizes time series values using scaling and quantization into a …

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

Deep Learning has been successfully applied to many application domains, yet its
advantages have been slow to emerge for time series forecasting. For example, in the well …

Unsupervised domain adaptation (UDA) aims at learning a machine learning model using a
labeled source domain that performs well on a similar yet different, unlabeled target domain …

An essential task in industrial intelligence is to accurately predict the remaining useful life
(RUL) of industrial equipment, and there has been tremendous progress in RUL prediction …

Human trajectory data produced by daily mobile devices has proven its usefulness in
various substantial fields such as urban planning and epidemic prevention. In terms of the …