LiveHouse-TS introduces an open‑world living benchmark for Time Series Foundation Models, evaluating them prequentially on real future data rather than static test windows. The benchmark captures continuous performance across seasonal changes, distribution shifts, and unexpected events, providing a more realistic assessment of model robustness. Experiments across 11 domains and 17 datasets show that model rankings can dramatically change under this live protocol.
By Haomin Wen, Ziyu Zhou, Qingxiang Liu, Siru Zhong, Yuxuan Liang
Time Series Foundation Models (TSFMs) have recently emerged as a highly promising paradigm for cross-domain zero-shot forecasting. However, existing evaluation protocols predominantly rely on static benchmarks with fixed historical test windows.
arXiv:2609.13956v1 Announce Type: new
Abstract: In this report, we release Tabby, a long context probabilistic time series foundation model, together with a complete and open recipe of how it was bui...
By Shifeng Xie, Bahaeddine Abdessalem, Zehao Xiao, Youssef Attia El Hili, Ambroise Odonnat, Zhiwei Dong, Lei Zan, Themis Palpanas, Jianfeng Zhang, Lujia Pan, Keli Zhang, Malik Tiomoko
arXiv:2607. 04919v1 Announce Type: new Abstract: Deploying a time series foundation model requires GPU infrastructure, engineering overhead, and carries no guarantee of improvement over XGBoost.
By Nicholas Tan Jerome, Frank Simon
arXiv:2606. 27438v1 Announce Type: new Abstract: Since its initial release in 2020, Darts has become a widely used open-source Python library for time series analysis.
By Zhihao Dai, Dennis Bader, Alain Gysi
arXiv:2610.00405v1 Announce Type: cross
Abstract: Time-series foundation models (TSFMs) perform strongly across forecasting tasks, but their per-series inference is ill-suited to neighbor-rich foreca...
By Hao-Nan Shi, Tong Wu, Chen-Cong Sun, Yuan Jiang, Han-Jia Ye, De-Chuan Zhan
arXiv:2601. 19040v2 Announce Type: replace Abstract: Time Series Foundation Models (TSFMs) are a powerful paradigm for time series analysis and are often enhanced by synthetic data augmentation to improve the training data quality.
By Junwei Deng, Chang Xu, Jiaqi W. Ma, Ming Jin, Chenghao Liu, Xu Zhang, Li Zhao, Jiang Bian
arXiv:2602. 16224v2 Announce Type: replace Abstract: Time series data are prone to noise in various domains, and training samples may contain low-predictability patterns that deviate from the normal data distribution, leading to training instability or convergence to poor local minima.
By Xu Zhang, Peng Wang, Yichen Li, Wei Wang
arXiv:2602. 12147v4 Announce Type: replace Abstract: Time series foundation models (TSFMs) are revolutionizing the forecasting landscape from specific dataset modeling to generalizable task evaluation.
By Zhongzheng Qiao, Sheng Pan, Anni Wang, Viktoriya Zhukova, Yong Liu, Xudong Jiang, Qingsong Wen, Mingsheng Long, Ming Jin, Chenghao Liu
arXiv:2606. 27282v1 Announce Type: new Abstract: Time-series forecasting research has been moving steadily toward larger architectures, from specialized transformers to general-purpose foundation models, on the assumption that capacity is what unlocks accuracy.
By Lang Huang, Jinglue Xu, Luke Darlow
The paper introduces a simple, model‑agnostic time‑domain augmentation called Sliding‑Window Reordering with Overlap Averaging. It transforms the joint input‑target sequence into overlapping windows, randomly reorders a fraction of them based on a variance criterion, and reconstructs the sequence by averaging overlaps to generate synthetic samples with controlled variation and minimal temporal distortion. Experiments show strong performance gains across nine long‑term forecasting benchmarks and four short‑term traffic benchmarks, with detailed ablations and diagnostics highlighting the effectiveness of each design choice.
By Jafar Bakhshaliyev, Johannes Burchert, Niels Landwehr, Lars Schmidt-Thieme
Time-series forecasting research has been moving steadily toward larger architectures, from specialized transformers to general-purpose foundation models, on the assumption that capacity is what unlocks accuracy. We take the opposite position: most of the gap can be closed at far lower cost by tuning preprocessing rather than scaling models.