Transformer-based foundation models have emerged as a dominant paradigm in time series analysis, offering unprecedented capabilities in tasks such as forecasting, anomaly detection, classification, trend analysis and many more time series analytical tasks. This survey provides a comprehensive overview of the current state of the art pre-trained foundation models, introducing a novel taxonomy to categorize them across several dimensions. Specifically, we classify models by their architecture design, distinguishing between those leveraging patch-based representations and those operating directly on raw sequences. The taxonomy further includes whether the models provide probabilistic or deterministic predictions, and whether they are designed to work with univariate time series or can handle multivariate time series out of the box. Additionally, the taxonomy encompasses model scale and complexity, highlighting differences between lightweight architectures and large-scale foundation models. A unique aspect of this survey is its categorization by the type of objective function employed during training phase. By synthesizing these perspectives, this survey serves as a resource for researchers and practitioners, providing insights into current trends and identifying promising directions for future research in transformer-based time series modeling.
View on arXiv@article{kottapalli2025_2504.04011,
title={ Foundation Models for Time Series: A Survey },
author={ Siva Rama Krishna Kottapalli and Karthik Hubli and Sandeep Chandrashekhara and Garima Jain and Sunayana Hubli and Gayathri Botla and Ramesh Doddaiah },
journal={arXiv preprint arXiv:2504.04011},
year={ 2025 }
}