arXiv Machine Learning August 21, 2026 By Taihua Chen, Xiang Ma, Yixin Zhang, Tailin Zhan, Manyu Sun, Lizhen Cui

Scale-Aware Pretraining of Time Series Foundation Models via Multi-Patch Token Alignment and Hybrid Masking

Read the original on arXiv Machine Learning →

arXiv:2608. 20005v1 Announce Type: new Abstract: Pretraining time series foundation models across heterogeneous datasets necessitates effective handling of varying sampling frequencies.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 10

Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models

arXiv:2606. 09861v1 Announce Type: cross Abstract: While Next-Token Prediction (NTP) has unified LLM pretraining, its adaptation to unbounded, continuous time series (TS) remains open.

By Yunhao Zhang, Ruiying Qi, Jiale Zheng, Jianfeng Zhang, Lujia Pan, Junchi Yan

llms nlp efficiency

arXiv Machine Learning

Sep 10

PatchFormer: A Patch-Based Time Series Foundation Model with Hierarchical Masked Reconstruction and Cross-Domain Transfer Learning for Zero-Shot Multi-Horizon Forecasting

arXiv:2601.20845v2 Announce Type: replace Abstract: Time series forecasting is a fundamental problem with applications in climate, energy, healthcare, and finance. Many existing approaches require do...

By Olaf Yunus Laitinen Imanov, Derya Umut Kulali, Taner Yilmaz

llms fine-tuning efficiency benchmarks

arXiv AI

Aug 14

Into the ORBIT for Time Series: Training Regimes for Foundation Models

arXiv:2608. 13262v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) have advanced primarily through architectural innovation, while training regimes for large-scale heterogeneous corpora remain under-explored.

By Hongjie Xia, Yiding Liu, Yifan Hu, Peiyuan Liu, Zewei Dong

llms nlp safety

arXiv Machine Learning

Jul 3

Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis

arXiv:2607. 01918v1 Announce Type: new Abstract: We present Zeus, a unified tuning-free Time Series Foundation Model (TSFM) that delivers superior performance across diverse analysis tasks without any task-specific fine-tuning.

By Yisong Fu, Zezhi Shao, Chengqing Yu, Yujie Li, Yongjun Xu, Xueqi Cheng, Fei Wang

llms nlp fine-tuning

arXiv AI

Jun 16

FlowState: Sampling-Rate-Equivariant Time-Series Forecasting

arXiv:2508. 05287v3 Announce Type: replace-cross Abstract: Existing time series foundation models (TSFMs), often based on transformer variants, lack adaptability to different sampling rates, struggle with generalization across varying context and target lengths, and are computationally inefficient.

By Lars Graf, Thomas Ortner, Stanis{\l}aw Wo\'zniak, Angeliki Pantazi

llms benchmarks

arXiv AI

Aug 18

Adapting LLMs to Time Series Forecasting via Temporal Heterogeneity Modeling and Representation Alignment

arXiv:2508. 07195v2 Announce Type: replace-cross Abstract: Recent advances have demonstrated that Large Language Models (LLMs) can be effectively adapted for time series forecasting, revealing strong potential beyond natural language tasks.

By Yanru Sun, Emadeldeen Eldele, Zongxia Xie, Yucheng Wang, Wenzhe Niu, Qinghua Hu, Chee Keong Kwoh, Min Wu

llms benchmarks safety

One email a morning, machine-written

Related stories

Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models

PatchFormer: A Patch-Based Time Series Foundation Model with Hierarchical Masked Reconstruction and Cross-Domain Transfer Learning for Zero-Shot Multi-Horizon Forecasting

Into the ORBIT for Time Series: Training Regimes for Foundation Models

Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis

FlowState: Sampling-Rate-Equivariant Time-Series Forecasting

Adapting LLMs to Time Series Forecasting via Temporal Heterogeneity Modeling and Representation Alignment