Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Yong, Su, Xingjian, Wang, Shiyu, Zhang, Haoran, Liu, Haixuan, Wang, Yuxuan, Ye, Zhou, Xiang, Yang, Wang, Jianmin, Long, Mingsheng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918436228038656
author Liu, Yong
Su, Xingjian
Wang, Shiyu
Zhang, Haoran
Liu, Haixuan
Wang, Yuxuan
Ye, Zhou
Xiang, Yang
Wang, Jianmin
Long, Mingsheng
author_facet Liu, Yong
Su, Xingjian
Wang, Shiyu
Zhang, Haoran
Liu, Haixuan
Wang, Yuxuan
Ye, Zhou
Xiang, Yang
Wang, Jianmin
Long, Mingsheng
contents We introduce Timer-S1, a strong Mixture-of-Experts (MoE) time series foundation model with 8.3B total parameters, 0.75B activated parameters for each token, and a context length of 11.5K. To overcome the scalability bottleneck in existing pre-trained time series foundation models, we perform Serial Scaling in three dimensions: model architecture, dataset, and training pipeline. Timer-S1 integrates sparse TimeMoE blocks and generic TimeSTP blocks for Serial-Token Prediction (STP), a generic training objective that adheres to the serial nature of forecasting. The proposed paradigm introduces serial computations to improve long-term predictions while avoiding costly rolling-style inference and pronounced error accumulation in the standard next-token prediction. Pursuing a high-quality and unbiased training dataset, we curate TimeBench, a corpus with one trillion time points, and apply meticulous data augmentation to mitigate predictive bias. We further pioneer a post-training stage, including continued pre-training and long-context extension, to enhance short-term and long-context performance. Evaluated on the large-scale GIFT-Eval leaderboard, Timer-S1 achieves state-of-the-art forecasting performance, attaining the best MASE and CRPS scores as a pre-trained model. Timer-S1 is released to facilitate further research.
format Preprint
id arxiv_https___arxiv_org_abs_2603_04791
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling
Liu, Yong
Su, Xingjian
Wang, Shiyu
Zhang, Haoran
Liu, Haixuan
Wang, Yuxuan
Ye, Zhou
Xiang, Yang
Wang, Jianmin
Long, Mingsheng
Artificial Intelligence
We introduce Timer-S1, a strong Mixture-of-Experts (MoE) time series foundation model with 8.3B total parameters, 0.75B activated parameters for each token, and a context length of 11.5K. To overcome the scalability bottleneck in existing pre-trained time series foundation models, we perform Serial Scaling in three dimensions: model architecture, dataset, and training pipeline. Timer-S1 integrates sparse TimeMoE blocks and generic TimeSTP blocks for Serial-Token Prediction (STP), a generic training objective that adheres to the serial nature of forecasting. The proposed paradigm introduces serial computations to improve long-term predictions while avoiding costly rolling-style inference and pronounced error accumulation in the standard next-token prediction. Pursuing a high-quality and unbiased training dataset, we curate TimeBench, a corpus with one trillion time points, and apply meticulous data augmentation to mitigate predictive bias. We further pioneer a post-training stage, including continued pre-training and long-context extension, to enhance short-term and long-context performance. Evaluated on the large-scale GIFT-Eval leaderboard, Timer-S1 achieves state-of-the-art forecasting performance, attaining the best MASE and CRPS scores as a pre-trained model. Timer-S1 is released to facilitate further research.
title Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling
topic Artificial Intelligence
url https://arxiv.org/abs/2603.04791