This repo focus on progress on Time Series Foundation Model.
- A Survey of Deep Learning and Foundation Models for Time Series Forecasting. Miller(University of Georgia), John A., Mohammed Aldosari, Farah Saeed, Nasid Habib Barna, Subas Rana, I. Budak Arpinar, and Ninghao Liu. link 🔗18
- Foundation Models for Time Series Analysis: A Tutorial and Survey. Yuxuan Liang(The Hong Kong University of Science and Technology(Guangzhou), Haomin Wen(Beijing Jiaotong University)) link 🔗26
- Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts. Xiaoming Shi(princeton University), Shiyu Wang, Yuqi Nie, Dianqi Li, Zhou Ye, Qingsong Wen, and Ming Jin. link 🔗0 code
- Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series. Ekambaram, Vijay(IBM Granite), Arindam Jati, Nam H. Nguyen, Pankaj Dayama, Chandra Reddy, Wesley M. Gifford, and Jayant Kalagnanam. link 🔗7 code
- Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting. Rasul, Kashif, Arjun Ashok, Andrew Robert Williams, Hena Ghonia, Rishika Bhagwatkar, Arian Khorasani, Mohammad Javad Darvishi Bayazi et al. link 🔗15 code
- Unified Training of Universal Time Series Forecasting Transformers. Woo, Gerald(Salesforce AI Research), Chenghao Liu, Akshat Kumar, Caiming Xiong, Silvio Savarese, and Doyen Sahoo. link 🔗31 code
- Chronos: Learning the Language of Time Series. Das, Abhimanyu(Google Research), Weihao Kong, Rajat Sen, and Yichen Zhou. link 🔗46 code
- Moment: A family of open time-series foundation models. Mononito Goswami, Konrad Szafer, Arjun Choudhry, Yifu Cai, Shuo Li, Artur Dubrawski. link 🔗22 code
- Timer: Generative Pre-trained Transformers Are Large Time Series Models. Yong Liu(Tsinghua University), Haoran Zhang, Chenyu Li, Xiangdong Huang, Jianmin Wang, Mingsheng Long. link 🔗4 code
- Large Language Models Are Zero Shot Time Series Forecasters. Nate Gruver(NYU), Marc Finzi(CMU), Shikai Qiu(NYU), and Andrew G. Wilson(NYU). link 🔗174 code
- A decoder-only foundation model for time-series forecasting. Das, Abhimanyu(Google Research), Weihao Kong, Rajat Sen, and Yichen Zhou. link 🔗55 code
