arXiv Machine Learning

Universal Redundancies in Time Series Foundation Models

arXiv Machine Learning
Jun 10

One Step Closer to Ground Truth: A Multi-Scale Residual-Aware Representation Learning Pipeline for Predicting Time Series Data

arXiv:2606. 10678v1 Announce Type: new Abstract: Transformer-based models have emerged as leading paradigms in time-series forecasting in recent years, employing self-attention mechanisms to capture long-range dependencies.

By Amrijit Biswas, Mustafa Kamal, Robin Krambroeckers, M. M. Lutfe Elahi, Sifat Momen, Nabeel Mohammed, Shafin Rahman
arXiv AI
Jul 1

Mantis: Lightweight Foundation Model for Time Series Classification

arXiv:2502. 15637v2 Announce Type: replace-cross Abstract: While foundation models have revolutionized various domains, their application to time series classification remains rather under-explored, with existing literature predominantly focused on forecasting.

By Vasilii Feofanov, Songkang Wen, Shifeng Xie, Simon Roschmann, Marius Alonso, Hongbo Guo, Romain Ilbert, Malik Tiomoko, Quentin Bouniot, Zeynep Akata, Lujia Pan, Jianfeng Zhang, Ievgen Redko
arXiv Machine Learning
Nov 5

Decouple to Reuse: Fine-Grained Knowledge Augmentation for Time Series Foundation Models

arXiv:2611. 05993v1 Announce Type: new Abstract: Time series forecasting is critical for demand prediction and resource management in modern Web services, yet applying pretrained Time Series Foundation Models (TSFMs) to downstream tasks remains challenging due to domain shifts.

By Yuqian Wu, Qingxiang Liu, Yuxin Guo, Weifeng Su, Jian Li, Pengfei Xu, Xi Chen, Yutao Yue, Yuxuan Liang
arXiv Machine Learning
Oct 3

Foundations without Fundamentals: Zero-Shot Blind Spots in Time Series FMs

The paper introduces SimpleTimeBench, a diagnostic suite testing basic temporal primitives like monotonic trends, periodic signals, and leading indicator covariates. It finds that prominent multivariate Time Series Foundation Models (Chronos‑2, Moirai, and Toto) often produce suboptimal zero‑shot forecasts for these simple patterns, and that fine‑tuning can improve specific tasks while harming performance on other fundamentals. These failures persist in real‑world sensor forecasting, indicating that current TSFMs may lack the inductive biases needed to capture straightforward relationships, thereby limiting their practical reliability.

By Nafiseh Ghoroghchian, Haipeng Zhang, Shuyi Han, Alex Labach, George Stein
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
arXiv Machine Learning
Sep 22

A Hybrid Attention Model Learning Unified Time-aware Patch Representation for Irregular Multivariate Time Series Forecasting

The paper introduces a hybrid attention model that learns a unified time‑aware patch representation for irregular multivariate time series (IMTS) forecasting. It employs a time‑aware patch encoding to embed variable‑length intra‑patch timestamps, a time bias attention mechanism to adjust for temporal misalignment and asynchronous cross‑channel dependencies, and a hybrid causal mask on a decoder‑only Transformer to balance historical context with autoregressive forecasting. The authors also curate VersaTSA, a 30 B‑observation dataset preserving native sampling sparsity, and demonstrate state‑of‑the‑art zero‑shot performance on three IMTS benchmarks while remaining competitive on regular MTS tasks.

By Zhihao Lin, Li Lin, Qi Zhang, Kaiwen Xia, Shuai Wang, Jialin Qiao
arXiv AI
Oct 9

Timer-M1: A Multivariate Time Series Foundation Model via Learning Primitives

Timer‑M1 is a pretrained multivariate time‑series foundation model that learns with primitives for zero‑shot forecasting. It uses a primitive‑based data synthesis and pretraining pipeline to generate series with shared temporal and relational patterns, assembling them into multivariate samples with distinct channel roles. The model employs gated two‑dimensional Transformer blocks that dynamically allocate cross‑variate attention, achieving top performance on several large‑scale forecasting benchmarks.

By Haoran Zhang, Haixuan Liu, Xingjian Su, Yong Liu, Zhi Chen, Yuxuan Wang, Jianmin Wang, Mingsheng Long