Foundation models for time series analysis: A tutorial and survey

Y Liang, H Wen, Y Nie, Y Jiang, M **, D Song… - Proceedings of the 30th …, 2024‏ - dl.acm.org
Time series analysis stands as a focal point within the data mining community, serving as a
cornerstone for extracting valuable insights crucial to a myriad of real-world applications …

Deep time series models: A comprehensive survey and benchmark

Y Wang, H Wu, J Dong, Y Liu, M Long… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Time series, characterized by a sequence of data points arranged in a discrete-time order,
are ubiquitous in real-world applications. Different from other modalities, time series present …

Chronos: Learning the language of time series

AF Ansari, L Stella, C Turkmen, X Zhang… - arxiv preprint arxiv …, 2024‏ - arxiv.org
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 …

A survey on time-series pre-trained models

Q Ma, Z Liu, Z Zheng, Z Huang, S Zhu… - … on Knowledge and …, 2024‏ - ieeexplore.ieee.org
Time-Series Mining (TSM) is an important research area since it shows great potential in
practical applications. Deep learning models that rely on massive labeled data have been …

[HTML][HTML] TimeGPT in load forecasting: A large time series model perspective

W Liao, S Wang, D Yang, Z Yang, J Fang, C Rehtanz… - Applied Energy, 2025‏ - Elsevier
Abstract Machine learning models have made significant progress in load forecasting, but
their forecast accuracy is limited in cases where historical load data is scarce. Inspired by …

AutoCTS++: zero-shot joint neural architecture and hyperparameter search for correlated time series forecasting

X Wu, X Wu, B Yang, L Zhou, C Guo, X Qiu, J Hu… - The VLDB Journal, 2024‏ - Springer
Sensors in cyber-physical systems often capture interconnected processes and thus emit
correlated time series (CTS), the forecasting of which enables important applications …

Time-moe: Billion-scale time series foundation models with mixture of experts

X Shi, S Wang, Y Nie, D Li, Z Ye, Q Wen… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Deep learning for time series forecasting has seen significant advancements over the past
decades. However, despite the success of large-scale pre-training in language and vision …

Self-supervised learning for accelerometer-based human activity recognition: A survey

A Logacjov - Proceedings of the ACM on Interactive, Mobile …, 2024‏ - dl.acm.org
Self-supervised learning (SSL) has emerged as a promising alternative to purely supervised
learning, since it can learn from labeled and unlabeled data using a pre-train-then-fine-tune …

Visionts: Visual masked autoencoders are free-lunch zero-shot time series forecasters

M Chen, L Shen, Z Li, XJ Wang, J Sun, C Liu - arxiv preprint arxiv …, 2024‏ - arxiv.org
Foundation models have emerged as a promising approach in time series forecasting (TSF).
Existing approaches either repurpose large language models (LLMs) or build large-scale …

Timedit: General-purpose diffusion transformers for time series foundation model

D Cao, W Ye, Y Zhang, Y Liu - arxiv preprint arxiv:2409.02322, 2024‏ - arxiv.org
With recent advances in building foundation models for texts and video data, there is a surge
of interest in foundation models for time series. A family of models have been developed …