English
Related papers

Related papers: TimeFound: A Foundation Model for Time Series Fore…

200 papers

This work studies the problem of time series analysis with generalist (or foundation) models, which are models trained across many data domains. Drawing inspiration from the widespread success of large language models, we consider the…

Machine Learning · Computer Science 2025-01-03 Sabera Talukder , Yisong Yue , Georgia Gkioxari

Conventional time-series forecasting methods typically aim to minimize overall prediction error, without accounting for the varying importance of different forecast ranges in downstream applications. We propose a training methodology that…

Machine Learning · Computer Science 2025-08-15 Luca-Andrei Fechete , Mohamed Sana , Fadhel Ayed , Nicola Piovesan , Wenjie Li , Antonio De Domenico , Tareq Si Salem

Inspired by recent advances in large language models, foundation models have been developed for zero-shot time series forecasting, enabling prediction on datasets unseen during pretraining. These large-scale models, trained on vast…

Machine Learning · Computer Science 2025-12-01 Morad Laglil , Emilie Devijver , Eric Gaussier , Bertrand Pracca

Periodicity is a fundamental characteristic of time series data and has long played a central role in forecasting. Recent deep learning methods strengthen the exploitation of periodicity by treating patches as basic tokens, thereby…

Machine Learning · Computer Science 2025-10-07 Yiming Niu , Jinliang Deng , Yongxin Tong

Time series foundation models (TSFMs) are revolutionizing the forecasting landscape from specific dataset modeling to generalizable task evaluation. However, we contend that existing benchmarks exhibit common limitations in four dimensions:…

Time series foundation models (TSFMs) demonstrate impressive zero-shot performance for time series forecasting. However, an important yet underexplored challenge is how to effectively finetune TSFMs on specific downstream tasks. While naive…

Unlike natural language processing and computer vision, the development of Foundation Models (FMs) for time series forecasting is blocked due to data scarcity. While recent efforts are focused on building such FMs by unlocking the potential…

Machine Learning · Computer Science 2024-10-10 Qingxiang Liu , Xu Liu , Chenghao Liu , Qingsong Wen , Yuxuan Liang

The proliferation of Time Series Foundation Models (TSFMs) has significantly advanced zero-shot forecasting, enabling predictions for unseen time series without task-specific fine-tuning. Extensive research has confirmed that no single TSFM…

Machine Learning · Computer Science 2025-09-26 Hao-Nan Shi , Ting-Ji Huang , Lu Han , De-Chuan Zhan , Han-Jia Ye

How to best develop foundational models for time series forecasting remains an important open question. Tokenization is a crucial consideration in this effort: what is an effective discrete vocabulary for a real-valued sequential input? To…

Time series foundation models (TSFMs) have become increasingly popular for zero-shot forecasting. However, for a new time series domain not fully covered by the pretraining set, performance can suffer. Therefore, when a practitioner cares…

Machine Learning · Computer Science 2026-03-04 Thomas L. Lee , Edoardo M. Ponti , Amos Storkey

As multimodal data proliferates across diverse real-world applications, leveraging heterogeneous information such as texts and timestamps for accurate time series forecasting (TSF) has become a critical challenge. While diffusion models…

Machine Learning · Computer Science 2025-12-09 Da Zhang , Bingyu Li , Zhuyuan Zhao , Junyu Gao , Feiping Nie , Xuelong Li

A foundation model is a machine learning model trained on a large and diverse set of data, typically using self-supervised learning-based pre-training techniques, that can be adapted to various downstream tasks. However, current research on…

Unlike traditional time-series forecasting methods that require extensive in-task data for training, zero-shot forecasting can directly predict future values given a target time series without additional training data. Current zero-shot…

Machine Learning · Computer Science 2025-03-05 Ting-Ji Huang , Xu-Yang Chen , Han-Jia Ye

Foundation models for time series imputation remain largely unexplored. Recently, two such models, TabPFN-TS and MoTM, have emerged. These models share a common philosophy that places them within the family of time-indexed foundation…

Machine Learning · Computer Science 2026-02-11 Etienne Le Naour , Tahar Nabil , Adrien Petralia , Ghislain Agoua

Time series foundation models (FMs) have emerged as a popular paradigm for zero-shot multi-domain forecasting. FMs are trained on numerous diverse datasets and claim to be effective forecasters across multiple different time series domains,…

Machine Learning · Computer Science 2025-05-20 William Toner , Thomas L. Lee , Artjom Joosen , Rajkarn Singh , Martin Asenov

Deep learning utilizing transformers has recently achieved a lot of success in many vital areas such as natural language processing, computer vision, anomaly detection, and recommendation systems, among many others. Among several merits of…

Machine Learning · Computer Science 2023-12-05 Lena Sasal , Tanujit Chakraborty , Abdenour Hadid

We introduce Sundial, a family of native, flexible, and scalable time series foundation models. To predict the next-patch's distribution, we propose a TimeFlow Loss based on flow-matching, which facilitates native pre-training of…

Machine Learning · Computer Science 2026-05-12 Yong Liu , Guo Qin , Zhiyuan Shi , Zhi Chen , Caiyin Yang , Xiangdong Huang , Jianmin Wang , Mingsheng Long

Time series forecasting is critical in numerous real-world applications, requiring accurate predictions of future values based on observed patterns. While traditional forecasting techniques work well in in-domain scenarios with ample data,…

Machine Learning · Computer Science 2024-11-26 Liran Nochumsohn , Michal Moshkovitz , Orly Avner , Dotan Di Castro , Omri Azencot

Transformer-based time series foundation models face a fundamental trade-off in choice of tokenization: point-wise embeddings preserve temporal fidelity but scale poorly with sequence length, whereas fixed-length patching improves…

Artificial Intelligence · Computer Science 2026-03-13 Sravan Kumar Ankireddy , Nikita Seleznev , Nam H. Nguyen , Yulun Wu , Senthil Kumar , Furong Huang , C. Bayan Bruss

The expanding instrumentation of processes throughout society with sensors yields a proliferation of time series data that may in turn enable important applications, e.g., related to transportation infrastructures or power grids.…

Databases · Computer Science 2024-10-29 Hao Miao , Ziqiao Liu , Yan Zhao , Chenjuan Guo , Bin Yang , Kai Zheng , Christian S. Jensen