Position: Universal Time Series Foundation Models Rest on a Category Error

2026-02-05 · Xilin Dai, Wanxu Cai, Zhijian Xu, Qiang Xu arxiv

This position paper argues that the pursuit of "Universal Foundation Models for Time Series" rests on a fundamental category error, mistaking a structural Container for a semantic Modality. We contend that because time series hold incompatible generative processes (e.g., finance vs. fluid dynamics), monolithic models degenerate into expensive "Generic Filters" that fail to generalize under distributional drift. To address this, we introduce the "Autoregressive Blindness Bound," a theoretical limit proving that history-only models cannot predict intervention-driven regime shifts. We advocate replacing universality with a Causal Control Agent paradigm, where an agent leverages external context to orchestrate a hierarchy of specialized solvers, from frozen domain experts to lightweight Just-in-Time adaptors. We conclude by calling for a shift in benchmarks from "Zero-Shot Accuracy" to "Drift Adaptation Speed" to prioritize robust, control-theoretic systems.

📄 PDF Abstract BibTeX arXiv:2602.05287

Code (0)

등록된 구현이 없습니다.

A Comparative Study of Adaptation Strategies for Time Series Foundation Models in Anomaly Detection

2026-01-01 · Miseon Park, Kijung Yoon arxiv

Time series anomaly detection is essential for the reliable operation of complex systems, but most existing methods require extensive task-specific training. We explore whether time series foundation models (TSFMs), pret…

parameter-efficient fine-tuning Time Series Anomaly Detection

On the Internal Semantics of Time-Series Foundation Models

2025-11-19 · Atharva Pandey, Abhilash Neog, Gautam Jajoo arxiv

Time-series Foundation Models (TSFMs) have recently emerged as a universal paradigm for learning across diverse temporal domains. However, despite their empirical success, the internal mechanisms by which these models re…

General Time-series Model for Universal Knowledge Representation of Multivariate Time-Series data

2025-02-05 · Cheng He, Xu Huang, Gangwei Jiang, Zhaoyi Li 외

Universal knowledge representation is a central problem for multivariate time series(MTS) foundation models and yet remains open. This paper investigates this problem from the first principle and it makes four folds of c…

Anomaly Detection Imputation Time Series Time Series Analysis

A Time-Series Foundation Model by Universal Delay Embedding

2025-09-15 · Zijian Wang, Peng Tao, Jifan Shi, Rui Bao 외 arxiv

This study introduces Universal Delay Embedding (UDE), a pretrained foundation model designed to revolutionize time-series forecasting through principled integration of delay embedding representation and Koopman operator…

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

2026-05-31 · Yunhao Zhang, Ruiying Qi, Jiale Zheng, Jianfeng Zhang 외 arxiv

While Next-Token Prediction (NTP) has unified LLM pretraining, its adaptation to unbounded, continuous time series (TS) remains open. To bridge the gap, we introduce UniTok, a universal tokenizer that transforms TS into …