Time-Series Foundation Models

Ask about this topic

Overview

Time-series foundation models learn reusable patterns from large collections of sequences, aiming to support tasks such as forecasting, classification, imputation, and anomaly detection across domains. Common approaches include Transformer models with patch or value tokenization, masked and contrastive pretraining, next-token prediction, and newer recurrent or state-space architectures; training data may mix real series with synthetic ones. Models are used zero-shot or adapted through fine-tuning, in-context examples, covariates, retrieval, and lightweight adapters, with benchmarks such as GIFT-Eval and UCR/UEA testing different capabilities. Transfer can reduce the need for task-specific training, but results vary with data and operating conditions: specialists may still win, and robustness to distribution shifts, long contexts, uncertainty, and fair evaluation remain open challenges.

Latest papers

CardsList

304 papers69 papers in the last four weeks, up 86% on the four weeks before. 0.4% of all new papers.

Jul 15, 2026

TEDDY: A Pediatric Foundation Model for Risk Forewarning from ICD-Coded Diagnostic Histories

Pediatric electronic health records capture developmentally structured clinical trajectories, yet their potential for generative healthcare foundation models remains largely unexplored. Here we present TEDDY (Temporal Event Decoder for Disease in Youth), a 1.84-million-parameter decoder transformer trained on approximately 73 million ICD-10 diagnoses from 1.6 million children at a single pediatric institution. TEDDY models longitudinal diagnosis trajectories and visit timing. Predictions were made before visit codes were revealed, limited to first occurrences, and evaluated against sex- and age-matched controls. Across 797 disease-onset prediction tasks spanning 16 ICD-10 chapters, TEDDY achieved a median AUC of 72.0%, outperforming same-data DenseNet (50.0%), CNN (57.2%), RNN (60.1%), and LSTM (62.7%) baselines on 96-99% of tasks. Performance held across sex and age and was strongest among lower-prevalence diagnoses; 202 of the 225 rarest conditions (90%) had 95% confidence intervals above chance. Predictive signal remained detectable more than two years before first recorded diagnosis, with median AUCs of 59.7% in the unrestricted analysis and 64.4% in a fixed-cohort sensitivity analysis. In asthma and attention-deficit/hyperactivity disorder benchmarks, AUCs were 79.3% and 84.7%, compared with 62.7% and 71.7% for the strongest comparators, including a general-purpose language model three orders of magnitude larger. Visit-timing predictions had a 3.0-day mean absolute restricted mean survival-time error over 365 days, although median and long-tail return intervals remained miscalibrated. Together, these results establish pediatric diagnostic histories as a substrate for compact generative models supporting broad, rare-disease, and long-horizon risk forecasting without population-scale data or billion-parameter models.

Matthew Brady Neeley, Jorge Botas, Johnathan Jia +5

Baylor College of Medicine

EHR Foundation ModelsClinical PredictionLongitudinal EHR ModelingElectronic Health RecordsTime-Series Foundation ModelsClinical Risk Prediction
AskPDF
Jul 14, 2026

The Spectrum Is Not Enough: When Context Helps Time-Series Forecasting

A growing family of indices scores how predictable a series is from its spectrum. Practitioners increasingly read these scores as answering a different question: whether adding context, a longer lookback, a retrieval plug-in, or a pretrained model, will help. These are not the same question. The value of context is a property of the operating point, not of the series. Any index built from the power spectrum is invariant under phase randomization, whereas the beyond-second-order value that retrieval and foundation models supply is not, because a phase-randomized series is asymptotically Gaussian. We state this as an impossibility result and isolate it with surrogate pairs that fix the spectrum and the marginal by construction. We then give a label-free, configuration-level diagnostic, the coverage deficit, whose principal term measures beyond-spectrum structure as the gain of analog over linear prediction. On seven benchmarks the prediction holds: window-keyed retrieval's value collapses across surrogate pairs (ECL median +33% ⁣→ ⁣−35%+33\%\!\to\!-35\%, p<10−40p{<}10^{-40}) while every spectral index stays frozen; a foundation model's value splits into a surviving second-order part and a small beyond-linear margin that collapses; a longer linear window's value survives. Leave-one-dataset-out, the structure term predicts the sign of beyond-spectrum value where the spectral indices trail it, and the reverse holds for the second-order mechanism. We introduce no new forecaster; the contribution is the distinction, a controlled comparison, and a diagnostic for the deployment decision. Code: https://github.com/KurbanIntelligenceLab/SINE

Mert Onur Cakiroglu, Mehmet Dalkilic, Hasan Kurban

Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington, Bloomington, IN, USA · College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar

Time Series ForecastingRetrieval-Augmented Time Series ForecastingTime-Series Foundation ModelsTime Series Modeling
AskPDF
Jul 14, 2026

Exploring Zero-Shot Foundation Models for Multivariate Time Series Anomaly Detection

Multivariate Time Series Anomaly Detection (MTSAD) is essential for reliability and safety in domains such as industrial process monitoring and financial risk management, yet conventional approaches rely on application-specific models that are costly to train and hard to scale. Foundation Models (FMs), pre-trained on broad data with strong zero-shot generalization, have recently become available for univariate time series forecasting, raising the question of whether they can address MTSAD without task-specific training. We investigate the zero-shot application of a univariate forecasting FM, TimesFM, to industrial MTSAD on the Secure Water Treatment (SWaT) benchmark, evaluating two strategies: treating the FM as a per-feature forecaster with thresholded prediction errors, and as an embedder whose intermediate representations feed standard outlier detectors. Neither of our proposed setups is competitive with established baselines; embeddings reveal only partial separation between normal and anomalous segments, insufficient for reliable detection. The cause is that the FM is too effective at capturing temporal dynamics, yielding low error even within fully anomalous windows, so persistent anomalies become indistinguishable from normal behavior. However, these observations yield valuable insights: the error peaks at anomaly boundaries, indicating FMs reliably detect distribution changes. We conclude that the proposed naive zero-shot FMs are unsuitable for MTSAD but promising for change-point detection.

Martin Uray, Saverio Messineo, Roland Kwitt +1

Josef Ressel Centre for Intelligent and Secure Industrial Automation, Salzburg University of Applied Sciences, Austria · Department of Artificial Intelligence and Human Interfaces, Paris Lodron University of Salzburg, Austria

Industrial Anomaly DetectionZero-Shot Anomaly DetectionTime-Series Anomaly DetectionTime-Series Foundation Models
AskPDF
Jul 13, 2026

NeuroECG: ECGFounder-Based Deep ECG Representation for EEG-Free Neurological Prognostication After Cardiac Arrest

Neurological prognostication after cardiac arrest commonly relies on electroencephalography (EEG). However, EEG demands high clinical resources. Bedside electrocardiography (ECG) is standard and low-cost. Yet, its value for predicting neurological outcomes remains underexplored. In this study, we propose NeuroECG, an ECGFounder-based deep representation framework for EEG-free auxiliary prognostication. NeuroECG adapts a pretrained ECG foundation model via task-specific fine-tuning. We implement a gradual unfreezing strategy on single-channel bedside monitoring ECG. Multiple ECG segments per patient are encoded into segment-level deep features. These embeddings are aggregated via quantile pooling (q = 0.24) and compressed using principal component analysis (PCA). Experiments on 412 ECG-available patients from the multicenter I-CARE database show that the adapted ECGFounder backbone achieves the best performance among ECG-only backbone baselines, with a test AUROC of 0.7333. We further combine the learned deep ECG representation with static clinical covariates. The proposed NeuroECG model achieves a test AUROC of 0.8077 and an AUPRC of 0.8970. These results support deep bedside ECG representations as a useful source of auxiliary prognostic information. Their integration with static clinical covariates improves prediction in an EEG-free setting. The source code is available at https://github.com/goddream66/NeuroECG

Jiajun Gao, Yi Zhao, Chenyang Xu +2

School of Economics and Management Xidian University Xi’an, China · School of Mechano-Electronic Engineering Xidian University Xi’an, China · School of Cyber Engineering Xidian University Xi’an, China +1

Representation LearningHealthcareElectrocardiographyClinical Outcome PredictionElectrocardiogram Representation LearningElectrocardiogram Foundation Models+1
AskPDF
Jul 8, 2026

Evaluating the Generalizability of Foundation Models for Extreme Environmental Events: Case Study of California Wildfire PM2.5

Wildfire smoke events produce extreme PM2.5_{2.5} concentrations that pose severe public health risks, yet forecasting rare, hazardous-level spikes remains a fundamental challenge. Time series foundation models (TSFMs), pretrained models offering zero-shot inference and efficient adaptation, perform strongly on general benchmarks, but their behavior under extreme out-of-distribution conditions is poorly understood. We present the first systematic benchmark comparing six TSFM configurations (zero-shot TimesFM, Chronos-2, Moirai-2, and Time-MoE, plus LoRA fine-tuned Chronos-2 and Time-MoE) against fully-trained baselines (LSTM, BiLSTM, Transformer) and naive persistence on a 12-year (2013--2025) hourly PM2.5_{2.5} dataset covering 1,375 wildfire incidents across 79 California monitoring sites. A leave-one-incident-out (LOIO) protocol evaluates generalization to unseen fires, using MAE, RMSE, and exceedance F1 at EPA AQI thresholds across 6-, 12-, and 24-hour horizons. Results reveal a consistent hierarchy. The BiLSTM achieves the lowest MAE (5.16 μg/m35.16\,μg/m^3) and the highest exceedance F1 at every threshold, including the Hazardous band (>225.5 μg/m3>225.5\,μg/m^3), reaching 0.63 versus at most 0.54 for any foundation model. Zero-shot TSFMs improve on persistence only modestly, and zero-shot Chronos-2 exhibits severe RMSE tail instability (23.4 μg/m323.4\,μg/m^3, negative R2R^2) from sporadic large errors. LoRA fine-tuning substantially improves both adapted families and largely repairs this instability, yet no foundation model surpasses the trained recurrent baselines on any metric. These findings challenge the assumption that larger pretrained models universally dominate environmental forecasting and provide actionable deployment guidance for wildfire air quality prediction.

Yongcan Huang, Li Jiang, Ze Yu Liu

College of Engineering, University of Georgia, Athens, Georgia, USA · Information System Department, UMBC, Baltimore, Maryland, USA · College of Graduate and Professional Studies, Trine University, Angola, Indiana, USA +1

Wildfire ForecastingOOD GeneralizationForecasting BenchmarksAir Quality PredictionTime-Series Foundation Models
AskPDF
Jul 8, 2026

TimEE: End-to-end Time Series Classification via In-Context Learning

Time series classification (TSC) is dominated by a two-stage paradigm: train a feature encoder -- either from scratch on the target dataset or via pretraining on large corpora -- and then fit a task-specific classifier on top. While effective, this decoupling optimizes representation learning independently of the classification objective, requires per-dataset training, and prevents the model from exploiting label information during inference. We introduce TimEE, a 4.5M-parameter foundation model for end-to-end TSC via in-context learning. Given a labeled support set and a query time series, TimEE directly outputs a predicted class distribution in a single forward pass with no per-dataset training required. Following the prior-data fitted network (PFN) framework, TimEE is meta-trained exclusively on synthetic TSC tasks, where each task contains time series with distinct class identities arising from structured distributional shifts in the generative process. Despite seeing no real time series during pre-training, TimEE ranks first in ROC AUC (and third on accuracy) on the UCR benchmark among all compared methods, which include both foundation models and supervised deep learning baselines. To our knowledge, TimEE is the first purely synthetic-pretrained model to reach state-of-the-art performance on the UCR benchmark. These results establish end-to-end ICL with synthetic priors as a compelling, largely unexplored direction for TSC, with scaling, prior design, and richer generation mechanisms as natural avenues for improvement. Code is publicly available at http://github.com/automl/timee.

Jaris Küken, Shi Bin Hoo, Martin Mráz +2

University of Freiburg · Zuse School ELIZA Darmstadt · Prior Labs +1

Synthetic Data PretrainingTime Series ClassificationIn-Context LearningClassificationTime-Series Foundation Models
AskPDF
Jul 8, 2026

Physical activities enable scalable foundation modelling for broad-spectrum health prediction

Wearable and mobile sensing technologies have demonstrated strong potential for health inference; however, most sensor models are designed for specific disease types, limiting their transferability across different health risks. Wearable foundation models offer a more generalizable approach in diverse health risk types. Nevertheless, most existing methods rely on high-frequency raw sensor data, raising concerns about privacy, computational overhead, and scalability across devices and populations. In this paper, we propose StepFM, a foundation model built solely on step counter data for broad-spectrum health prediction. Leveraging the ubiquity and low-dimensional nature of step data, StepFM provides a practical, privacy-preserving, and computation-efficient alternative to traditional sensor-based models. We design a scalable pre-training framework that captures temporal dynamics and behavioral patterns from large-scale step sequences, enabling transfer across more than 20 health risk prediction tasks spanning diverse devices, new regions, and novel disease types. Extensive experiments demonstrate that StepFM achieves strong performance compared to existing methods while maintaining robustness across heterogeneous settings. Furthermore, our analysis reveals interpretable and generalizable relationships between physical activity patterns and various health risks, offering new insights into activity-based health modeling. Our work establishes step-based sensing as a viable foundation for scalable and real-world health monitoring.

Zhenghuang Wu, Yuyao Zhu, Songlin Xu

Beihang University, Beijing, China · University of Science and Technology of China, Hefei, China · The Hong Kong Polytechnic University, Hong Kong SAR, China

Wearable Health MonitoringTime-Series Foundation ModelsClinical Risk Prediction
AskPDF
Jul 7, 2026

RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models

Recent years have witnessed the emergence of multivariate modeling using time series foundation models (TSFMs), which achieve advanced zero-shot generalization. Modern multivariate TSFMs are predominantly pretrained on multivariate synthetic data, which is easier to scale but may fail to capture the complex temporal dynamics and cross-variable relationships present in real-world time series. This raises a key question: Whether and to what extent the leading TSFMs trained with the real-world corpus perform better than those trained with synthetic data? To answer this, we establish the RMISC corpus, a considerably large-scale, high-quality, openly accessible, real-world, and multivariate time series archive that contains around 200 datasets and 142 billion time points across diverse domains. Furthermore, we pretrain four advanced TSFMs on univariate, synthetic multivariate, and real-world multivariate data and evaluate their zero-shot generalization capabilities on standard in-distribution and out-of-distribution benchmarks. Experimental results show that incorporating real-world multivariate data predominantly improves the generalization performance for both univariate and multivariate TSFMs. These results provide a deeper understanding of how real-world multivariate data contributes to the development of stronger TSFMs.

Qian Sun, Yong-Ming Tian, Jia-Wei Huang +2

State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China · School of Intelligent Science and Technology, Nanjing University, Suzhou, China · Nanjing University – Siemens Joint Research Center on Industrial AI, Suzhou, China +1

Synthetic Data PretrainingMultivariate Time Series ForecastingZero-Shot Time Series ForecastingTime-Series Foundation Models
AskPDF
Jul 7, 2026

Inertia-1: An Open Exploration of Wearable Motion Foundation Models

Wearable motion sensing provides a continuous and scalable window into human behavior and health, making it a natural fit for foundation models, yet its pretraining and scaling principles remain poorly understood. Prior work studies isolated design choices, such as sensor placement or sampling frequency, often under fixed settings and narrow downstream tasks that fail to capture real-world sensing diversity. We introduce Inertia-1, a fully open exploration of wearable motion foundation models. Using massive corpora of accelerometer data from global sources spanning more than 18.2M hours, we build a controlled framework for studying the full lifecycle of wearable motion foundation models, covering data choices such as sensor modality, device placement, sampling rate, window length; model choices such as architectures and model size; and training choices such as pretraining objective and data scale. Extensive evaluations across 15 datasets spanning human activity recognition, freezing-of-gait detection, and disease prediction reveal intriguing findings for building motion foundation models that generalize across tasks and sensing conditions. Collectively, Inertia-1 not only presents state-of-the-art recipes for diverse downstream tasks, but also serves as a comprehensive, practical, and open cookbook for wearable motion representation learning.

Zongzhe Xu, Aakarsh Anand, Sarah Jiang +4

University of California, Los Angeles · Duke University · John Hopkins University

Human Activity RecognitionWearable SensingMotion Representation LearningTime-Series Foundation Models
AskPDF
Jul 6, 2026

When Do Foundation Models Pay Off? A Break-Even Analysis of Pretrained Time Series Forecasters

Deploying a time series foundation model requires GPU infrastructure, engineering overhead, and carries no guarantee of improvement over XGBoost. We provide the first systematic break-even analysis answering when this investment pays off. Across 30 benchmark datasets, we compare zero-shot and LoRA fine-tuned foundation models (Chronos, Moirai, Lag-Llama) against classical baselines (Naive, ETS, ARIMA, XGBoost) at six training set sizes from 2% to 100% of available data. Foundation models outperform classical methods at every evaluated training fraction on 15 of 30 datasets -- GPU deployment is unconditionally justified on these regardless of data volume. On 6 datasets, classical methods surpass zero-shot foundation models with as little as 2% of training data (21-2,768 samples); on the remaining 9, break-even ranges from 24 to 8,361 samples. One robust deployment rule requires no model training: if n_train < 700 and seasonality is non-negligible, use FM zero-shot and skip fine-tuning -- this resolves 10 of 30 deployment decisions immediately. Contrary to common practice, LoRA fine-tuning can actively degrade performance on short series. We operationalise these findings as a two-step decision framework -- compute dataset length and seasonality strength, run a brief 5-10% pilot only if needed -- enabling practitioners to make the FM-versus-classical decision before committing to full infrastructure. Four dataset features motivate mechanistic hypotheses for the remaining cases, though reliable automated prediction at this benchmark scale remains an open problem. Code, benchmark, and decision tools are available at https://github.com/nicolaisi/fm-breakeven.

Nicholas Tan Jerome, Frank Simon

Karlsruhe Institute of Technology (KIT) Eggenstein-Leopoldshafen, Germany

Zero-Shot Time Series ForecastingTime Series ForecastingForecasting BenchmarksTime-Series Foundation ModelsTime Series Modeling
AskPDF
Jul 3, 2026

MorphologyFM: A Foundation Model for Morphology-Aware Representation Learning from ECG and Pulse Oximetry Waveforms

Foundation models have recently emerged as a powerful paradigm for learning transferable representations from large scale biomedical data, yet existing approaches for physiological waveforms primarily optimize reconstruction or forecasting objectives that do not explicitly preserve clinically meaningful waveform morphology. Electrocardiograms (ECGs) and pulse oximetry (SpO2) waveforms encode rich cardiovascular and hemodynamic information through their morphological structure. In this work, we introduce MorphologyFM, a multimodal foundation model pretrained on paired ECG and SpO2 waveforms from the MIMIC critical care database using a morphology aware self supervised learning objective. MorphologyFM combines morphology guided masking, cross modal representation learning, and contrastive latent alignment to learn representations that capture clinically relevant physiological structure without requiring manual annotations. We evaluate MorphologyFM across multiple downstream prediction tasks, including arrhythmia classification, hypoxemia prediction, mortality prediction, and length of stay estimation, demonstrating consistent improvements over representative self supervised learning methods, including Masked Autoencoders (MAE), contrastive learning, Barlow Twins, and Joint Embedding Predictive Architectures (JEPA). Furthermore, we show that jointly modeling ECG and SpO2 waveforms produces more transferable representations than single modality pretraining. Our results establish waveform morphology as a powerful inductive bias for self supervised physiological representation learning and introduce MorphologyFM as a general purpose foundation model for continuous physiological monitoring.

Saiyang Feng, Yuanyun Zhang, Shi Li

University of the Chinese Academy of Sciences · Columbia University

Self-Supervised Time Series Representation LearningCross-Modal Representation LearningElectrocardiographyRepresentation LearningTime-Series Foundation ModelsElectrocardiogram Foundation Models+1
AskPDF
Jul 3, 2026

Modular Foundation Models for Time-Series Perception in Digital Twins

Engineering Digital Twins and Prognostics and Health Management (PHM) systems rely on robust perception modules to extract actionable information from heterogeneous and non-stationary time-series data. However, most existing approaches remain task-specific, data-hungry, and difficult to integrate into scalable monitoring and decision-making pipelines. Moreover, purely data-driven models often lack robustness and transferability across varying operating conditions. To address these challenges, this paper proposes a modular foundation model for time-series perception based on a collection of pretrained representation encoders. The framework leverages self-supervised learning on heterogeneous datasets to learn transferable and task-agnostic representations, which can be reused across multiple PHM tasks. A gating mechanism is introduced to dynamically select relevant encoders for a given target dataset, enabling conditional computation and adaptive model composition. The selected representations are projected into a shared latent space and aggregated using a Transformer-based self-attention module that explicitly models cross-encoder interactions. The resulting architecture supports multiple downstream tasks, including imputation, long-term forecasting, and few-shot learning, through lightweight task-specific heads, while keeping pretrained encoders frozen during adaptation. Extensive ablation studies demonstrate the complementary roles of self-supervised pretraining, encoder selection, representation alignment, and adaptive aggregation. Experimental results on the ETT benchmark show competitive performance across tasks, while a real-world industrial case study on virtual sensing for hydro-generator rotor temperature highlights the practical relevance of the approach.

Quang Hung Pham, Ryad Zemouri, Martin Gagnon +1

Hydro-Québec · 75, boulevard René-Lévesque Ouest · Montréal, Québec, Canada

Self-Supervised Time Series Representation LearningTime Series ForecastingPredictive MaintenanceTime-Series Foundation ModelsModular Neural Networks
AskPDF
Jul 2, 2026

QuantFlow: A Federated Mamba-Based Post-Transformer Foundation Model for Time-Series Forecasting

Time-series forecasting supports decisions in finance, en-ergy, transportation, public health, and industrial monitoring. Recent foundation models improve transfer across forecast-ing tasks, but many depend on centralized data and Trans-former attention, which restricts their use for long, high-di-mensional, and privacy-sensitive signals. This paper presents QuantFlow, a probabilistic forecasting framework that com-bines inverted sequence embedding, bidirectional Mamba state-space decoders, quantile regression, and federated learning. Each variable is embedded over the complete ob-servation window, processed in forward and reverse direc-tions, and projected to five conditional quantiles. TSMixup expands temporal diversity through Dirichlet-weighted inter-polation while preserving sequence structure. Experiments cover cryptocurrency, traffic, electricity, Electricity Trans-former Temperature, influenza, and weather data. QuantFlow obtains mean squared errors of 0.2834 on ETTm1 and 0.2218 on Weather, and a 20-client non-IID deployment retains use-ful accuracy after three communication rounds without cen-tralizing raw records. The results indicate that selective state-space modelling is a promising basis for scalable, uncer-tainty-aware, and privacy-conscious time-series prediction, while also revealing limitations on irregular epidemiological signals and long-horizon generalization.

Shah Nawaz Haider, Steve Austin, Arnab Barua +2

Department of Computer Science and Engineering, University of Science and Technology Chittagong · Department of Electrical and Electronic Engineering, University of Science and Technology Chittagong · Faculty of Science, Engineering and Technology, University of Science and Technology Chittagong

Selective SSMsTime Series ForecastingTime-Series Foundation ModelsProbabilistic Time Series Forecasting
AskPDF
Jul 2, 2026

Evaluating Time Series Foundation Models for Electricity Price Forecasting: Contamination Risk, Distributional Shifts, and Covariate Dependence

Time series foundation models (TSFMs) have shown strong zero-shot forecasting performance, but their generalization in covariate-driven, non-stationary settings is underexplored. Electricity price forecasting (EPF) presents a challenging testbed due to complex temporal dependencies, distributional shifts, and strong reliance on structural and contextual information. We propose a two-dataset-benchmarking framework for EPF to mitigate contamination risk and enable fair evaluation of TSFMs. We examine key aspects of EPF including point and probabilistic forecasting performance, tail behavior, price spikes, and comparisons against domain-specific methods. We find that TSFMs are highly competitive and often outperform general-purpose baselines. Yet, their performance depends critically on covariate support, and they do not consistently surpass domain-specific methods tailored to EPF. Interestingly, simple ensembles of TSFMs and domain-specific methods appear to have significant potential, suggesting that the two approaches capture complementary predictive information.

Zhenghua Pan, Ahmed Aziz Ezzat

Department of Industrial & Systems Engineering, Rutgers, The State University of New Jersey, USA.

Zero-Shot Time Series ForecastingElectricity Price ForecastingTime Series ForecastingForecasting BenchmarksNon-Stationary Time Series ForecastingTime-Series Foundation Models+1
AskPDF
Jul 2, 2026

Probabilistic Low-Voltage Peak Load Forecasting with Time Series Foundation Models Evaluated on Application-Oriented Metrics

Low-voltage load forecasting is an important component in current and future energy systems with a high degree of electrification and decentralized generation. However, current forecasting methods require significant manual effort, often lack uncertainty estimation and proper peak prediction, and they are often not adequately evaluated in terms of grid requirements. In the present study, we provide an extensive evaluation of short-term net load forecasts of 200 real-world low-voltage feeders with a focus on the rapidly evolving time series foundation models. Our study compares Chronos-Bolt, Chronos-2 and TabPFN-TS to six baseline models and demonstrates superior performance, in particular for Chronos-2. An ablation study, in which weather covariates are omitted, shows that time series foundation models adapt to increased uncertainty, despite the importance of weather information. A novel application-oriented metric links the model's forecasting capabilities in peak prediction to the trade-off in grid asset planning and operation between cost reduction and minimizing the risk of failure.

Benedikt Kaas, Manuel Treutlein, Hannes Benedikt Gerber +5

Karlsruhe Institute of Technology (KIT), Germany and Netze BW GmbH, Germany · Netze BW GmbH, Germany · Karlsruhe Institute of Technology (KIT), Germany

Time Series ForecastingElectricity Load ForecastingTime-Series Foundation ModelsProbabilistic Time Series Forecasting
AskPDF
Jul 2, 2026

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

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. Unlike prior studies that primarily focus on zero-shot forecasting but require task-specific tuning for other tasks, Zeus bridges this gap by addressing two fundamental challenges in multi-task generalization. First, to reconcile point-level granularity with long-sequence scalability, Zeus incorporates a multi-scale Transformer featuring point-wise tokenization and a U-shaped hierarchy, effectively balancing fine-grained fidelity with computational efficiency. Second, to accommodate varying inductive biases across different tasks, Zeus introduces Multi-Objective Temporal Masking (MOTM), a unified strategy that supports heterogeneous tasks (e.g., extrapolation, interpolation, and global abstraction) within a single framework. Extensive experiments across five representative tasks demonstrate that Zeus consistently achieves competitive results in tuning-free settings, underscoring its potential as a general-purpose TSFM.

Yisong Fu, Zezhi Shao, Chengqing Yu +4

State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Xiamen Institute of Data Intelligence

Zero-Shot Time Series ForecastingMulti-Task LearningSequence ModelingTime-Series Foundation ModelsMultiscale Time-Series Modeling
AskPDF
Jul 1, 2026

TiRex-2: Generalizing TiRex to Multivariate Data and Streaming

We introduce TiRex-2, a recurrent xLSTM-based time series foundation model that generalizes the univariate TiRex to multivariate forecasting with both past and future covariates. Real-world forecasting is inherently sequential: observations arrive continuously, variables evolve jointly, and a subset of covariates is known ahead of time. Existing Transformer-based time series foundation models capture cross-variate dependencies but incur quadratic complexity in context length and require full-history recomputation as new observations arrive. TiRex-2 addresses these limitations through a memory-centric recurrent design that operates at constant per-patch cost under streaming. The model combines a bidirectional time mixer with an asymmetric grouped-attention variate mixer, enabling the integration of future-known covariates while preserving strict causality over target variables. To our knowledge, this is the first time series foundation model that achieves this combination of properties. To support scalable multivariate pretraining, we propose a synthetic coupling pipeline that composes diverse multivariate samples on the fly from large univariate corpora. Empirically, TiRex-2 achieves state-of-the-art zero-shot performance on GIFT-Eval and fev-bench, remains stable when streamed to arbitrary context lengths, and maintains constant inference cost per patch. The model uses 38.4M active parameters in univariate mode, with an additional 44.1M parameters activated for multivariate forecasting.

Patrick Podest, Marco Pichler, Elias Bürger +7

ELLIS Unit Linz, LIT AI Lab & Institute for Machine Learning, JKU Linz, Austria · NXAI Lab, Linz, Austria · NXAI GmbH, Linz, Austria +1

Multivariate Time Series ForecastingZero-Shot Time Series ForecastingTime Series ForecastingTime-Series Foundation ModelsTime Series Forecasting with Covariates
AskPDF
Jun 30, 2026

CLOUDADV: Decision-Aligned Instance Sizing with Zero-Shot Foundation Models under Drift

Cloud virtual machines are often overprovisioned, creating avoidable cost and operational inefficiency. We present CLOUDADV, an interactive engineer-facing advisory system for cloud instance sizing under workload drift. The system combines zero-shot time-series forecasting with bounded recommendation generation across day-, week-, and month-scale planning horizons. For each query, CLOUDADV constructs a structured decision context from historical utilization, forecast summaries, current VM metadata, candidate instance options, pricing, and explicit sizing heuristics. A higher-capacity LLM is used offline to generate reference recommendations, while a smaller production model is evaluated on the same prompts to assess deployment-time alignment under latency and cost constraints. Evaluation prioritizes downstream recommendation quality using simulated Azure cost savings and ex-post exceedance, with rolling-origin forecast accuracy reported as a secondary diagnostic against classical and supervised baselines. In a case study of seven production VMs, the reference recommendations reduce simulated monthly cost from about $1,503 to $708, yielding $795/month in savings (52.9%) under conservative heuristic constraints, while the highest observed exceedance rate among downgraded cases is 1.5%. Although Chronos-2 does not minimize every forecasting metric, it often induces recommendation patterns similar to those of a supervised per-VM baseline. These results suggest that zero-shot foundation models can support decision-aligned provisioning in non-stationary cloud environments while reducing the operational burden of repeated per-tenant retraining, revalidation, and redeployment.

Jack Bell, Giacomo Carfi, Gerlando Gramaglia +3

Department of Computer Science University of Pisa Pisa, Italy · Independent Researcher Sintra Consulting Limited Arezzo, Italy · Department of AI, Data and Decision Science Luiss University Rome, Italy

AI-Assisted Decision MakingCloud ComputingTime-Series Foundation Models
AskPDF
Jun 29, 2026

Temporal Feature Extractors in EEG Foundation Models: A Controlled Comparison Including a Pretrained Time-Series Model

Electroencephalography (EEG) foundation models aim to learn generalizable representations from large-scale brain recordings. However, the role of temporal feature extractors and whether pretrained time-series foundation models (TSFMs) can be effectively transferred to this setting remains underexplored. We conduct a controlled comparison of three temporal feature extraction strategies, including a linear baseline, a convolutional encoder, and a frozen pretrained TSFM (MOMENT), within a unified EEG foundation model. We evaluate their impact on representation quality using two downstream tasks: motor imagery and emotion recognition. Results reveal different trends across the evaluated benchmarks. On the motor imagery dataset, simple temporal representations perform competitively, whereas the emotion dataset benefits from richer temporal modeling. Although not specifically adapted to EEG, the pretrained TSFM serves as an effective temporal feature extractor, suggesting that general-purpose time-series representations can be transferred as frozen temporal feature extractors within EEG foundation models.

Ayşe Betül Yüce, Chris Joey Leffler, Sarun Varghese +2

Otto von Guericke University Magdeburg, Artificial Intelligence Lab, Faculty of Computer Science, Magdeburg, Germany · Otto von Guericke University Magdeburg, Knowledge Management and Discovery Lab, Faculty of Computer Science, Magdeburg, Germany

EEG DecodingTime-Series Foundation ModelsEEG Foundation Models
AskPDF
Jun 27, 2026

MACROCAST: A Vintage-Consistent Time Series Foundation Model for Real-Time Macroeconomic Forecasting

We introduce MACROCAST, a lightweight Time Series Foundation Model (TSFM) for real-time macroeconomic forecasting. Existing TSFMs suffer from data leakage in two forms: temporal contamination, as the model may have seen the realized values of the series it forecasts, and revision bias, as training on fully revised data diverges from the preliminary, vintage-specific releases available to real-time forecasters. MACROCAST is, to our knowledge, the first TSFM that rules out both forms of leakage entirely: at no stage of training is the model exposed to information that would not have been available to a forecaster in real time. We train MACROCAST first on purely synthetic time series in approximately one GPU-day and then fine-tune it on synthetic time series drawn from Bayesian VARs, dynamic factor models, and ARIMA specifications estimated on vintage-specific ALFRED data. Because pretraining uses only simulated data and fine-tuning uses only real-time vintages, no observed future or revised value ever enters the model; each fine-tuning run takes nine minutes. Evaluated on the FRED-MD database in a genuine real-time out-of-sample exercise, MACROCAST improves on the AR(1) benchmark for roughly 80% of series-horizon pairs, matches or surpasses Chronos-2 -- the strongest currently available TSFM -- and outperforms the Bayesian VAR and dynamic factor model benchmarks, all in a data-leakage-free manner.

Andrea Carriero, Davide Pettenuzzo, Shubhranshu Shekhar

School of Economics and Finance, Queen Mary University of London. · School of Business and Economics, Brandeis University.

Data LeakageTime Series ForecastingTemporal Data LeakageTime-Series Foundation ModelsTime Series Modeling
AskPDF
Jun 26, 2026

NIVA: A Multimodal Foundation Model for Actionable Earth System Intelligence

Recent advances in AI-driven weather and climate modeling have improved forecast skill while reducing computational cost. However, existing data-driven approaches are limited in their ability to model coupled Earth system dynamics, which is required for extending predictability beyond the ~2-week horizon. To address this, we introduce NIVA, a multimodal foundation model designed to learn unified representations across Earth system components. While the full framework targets atmosphere, ocean, ice, and land interactions, we focus here on a two-modality setting (ocean and atmosphere) as a controlled proof of concept to evaluate whether foundation models can learn coupled dynamics. Trained on large-scale Earth system simulations, NIVA learns physically meaningful cross-modal structure, providing a foundation for subseasonal-to-seasonal prediction. As initial validation, we show that NIVA captures key modes of climate variability through accurate prediction of major climate indices.

Anisha Pal, Aodhan Sweeney, Kyle Heyblom +1

Independent Researcher · Work done while at Planette AI · Planette AI, USA.

Climate ScienceMultimodal PretrainingTime Series ForecastingClimate ModelingTime-Series Foundation Models
AskPDF
Jun 26, 2026

Are Time-Series Foundation Models Ready for E-Nose Data? An Empirical Assessment of Their Embeddings

Inspired by advances in natural language processing and computer vision, "time-series foundation models" (TSFMs) have recently been introduced with the promise of strong generalization across diverse time-series tasks, including forecasting, classification, and anomaly detection, as well as across domains such as healthcare, climate science, and manufacturing. However, their utility for gas-sensing data remains largely unexplored. To address this gap, this paper systematically evaluates recent TSFMs on electronic nose (E-Nose) data. In particular, we investigate whether embeddings produced by representative TSFMs, including Chronos-2 and MOMENT, provide effective representations for gas identification and concentration prediction. Specifically, we show that fine-tuning is necessary to achieve satisfactory performance on E-Nose data, and fusing TSFM embeddings with representations learned by specialized predictive models can further improve the performance, suggesting both the potential and limitations of current TSFMs for gas-sensing applications.

Taeyeong Choi, Mohammed Kamruzzaman

Department of Information Technology Kennesaw State University Marietta, GA 30060, USA · Department of Agricultural and Biological Engineering University of Illinois Urbana-Champaign Urbana, IL 61801, USA

Time Series ClassificationTime Series Representation LearningTime-Series Foundation Models
AskPDF
Jun 25, 2026

Unified Zero-Shot Time Series Forecasting: A Darts Foundation

Since its initial release in 2020, Darts has become a widely used open-source Python library for time series analysis. A series of foundation models have recently claimed accuracy improvements in zero-shot forecasting, promising a paradigm shift from training custom models to harnessing pre-trained general-purpose forecasters. Foundation models, however, are often released as isolated packages with fragmented interfaces and limited interoperability with common tooling, making joint evaluation and integration within complete pipelines difficult. In Darts, we developed a unified FoundationModel\texttt{FoundationModel} class collection (Chronos-2, TimesFM 2.5, TiRex, PatchTST-FM) that provides standardized, full-cycle forecasting interfaces with minimal external dependencies for integrating foundation models into the ecosystem. Existing Darts pipelines can now use foundation models with only a name change; new pipelines can use them for zero-shot or fine-tuned forecasting, uncertainty estimation, and backtesting, combined with data processing and evaluation tooling, all within a unified framework.

Zhihao Dai, Dennis Bader, Alain Gysi

Energy and Power Group, Department of Engineering Science, University of Oxford, UK · Unit8 SA, Switzerland

Zero-Shot Time Series ForecastingTime-Series Foundation Models
AskPDF
Jun 19, 2026

RocketPFN: Accurate Time Series Classification via In-Context Learning

We introduce RocketPFN, a training-free pipeline for time series classification that combines random convolutional feature extraction (Rocket) with in-context classification via a pretrained tabular foundation model (TabPFN v2.5). On 92 UCR datasets (30-resample protocol), RocketPFN matches HC2, the strongest published method on the archive, in mean accuracy (both 0.900, Wilcoxon p=0.50), with no training on the target data and a median inference time of 30 seconds per fold. It also significantly outperforms every individual classifier in the HC2 ensemble. On UEA (20 datasets) the difference is likewise not statistically significant. A separate comparison concerns TSC foundation models: when paired with the same downstream classifier, MOMENT, Mantis, and MantisV2 are all significantly outperformed by RocketPFN using fewer extracted features and no learned parameters (p<0.001 in each case). This holds even when the encoders were pretrained on corpora that include the UCR training samples. We propose this two-stage pipeline as a reference point for evaluating zero-shot TSC foundation models.

Franco Martino O'Rourke, Ana Trisovic, Dimitris Bertsimas

Time Series ClassificationClassificationTime-Series Foundation Models
AskPDF
Jun 17, 2026

Understanding Key Features of Time Series Foundation Models from Epidemic Forecasting

Seasonal influenza infects millions of people and causes substantial morbidity and mortality in the United States each year, making accurate short-term forecasting a core public-health need. Reliable forecasts of epidemic time series can inform vaccination timing, hospital staffing, and resource allocation, yet the comparative behavior of modern forecasting architectures on infectious-disease surveillance data remains insufficiently characterized. We address this gap through a systematic evaluation of regional influenza forecasting using influenza-like illness surveillance and influenza-associated hospitalization time series under both temporal and spatial generalization settings for 1-4-week-ahead prediction. We compare classical neural network architectures, numerical transformer-based models, pretrained time series foundation models, and LLM-based forecasting approaches. Across tasks, we demonstrate that a mixture-of-experts model that fuses multiple pretrained forecasters achieves the strongest overall performance, indicating that heterogeneous pretrained representations provide complementary predictive information. Our results further show that numerical transformer-based models produce reliable forecasts, while pretraining provides the largest gains at longer horizons, particularly when the pretraining domain is mechanistically aligned with influenza dynamics. In contrast, LLM-based time series methods underperform relative to numerical forecasters in this setting. Finally, we examine hospitalization information as both an auxiliary covariate and a pretraining source. Hospitalization signals provide complementary improvements in selected settings and clarify when additional surveillance streams enhance the robustness of multi-horizon forecasting. These findings provide actionable guidance on model selection, pretraining strategy, and auxiliary-signal use for influenza preparedness.

Alireza Jafari, Judy Fox, Geoffrey C. Fox +2

Department of Computer Science, School of Engineering and Applied Science, University of Virginia, Charlottesville, VA 22904 USA · School of Data Science, University of Virginia, Charlottesville, VA 22904 USA · Biocomplexity Institute and the Department of Computer Science, School of Engineering and Applied Science, University of Virginia, Charlottesville, VA 22904 USA +1

Epidemic ForecastingLLM-Based Time Series ForecastingSpatiotemporal ForecastingTime-Series Foundation Models
AskPDF
Jun 16, 2026

Do Time Series Foundation Model Benchmarks Hide Regime-Dependent Failures? Evidence from Traffic Speed Forecasting

Standard benchmarks evaluate time series foundation models (TSFMs) using aggregate metrics, but these can mask severe failures in critical operating regimes. We introduce regime-stratified evaluation and apply it to three TSFMs on two standard traffic speed benchmarks. Traffic exhibits abrupt regime switching between free-flow and congested states, producing bimodal speed distributions during transitions. When we stratify by traffic regime, both accuracy and prediction-interval coverage degrade sharply during transitions: transition-regime MAE reaches 11 mph (versus 3 mph overall), and empirical coverage of 90% prediction intervals drops as low as 55%. These failures are invisible in aggregate metrics because free-flow observations dominate the sample. A simple historical conditional baseline (sampling from per-sensor training distributions) achieves better transition coverage than any TSFM, but has far worse overall accuracy. We propose bimodal mixture augmentation (BMA), a post-hoc method that combines TSFM forecasts with historical distributional knowledge, approaching the historical baseline's transition coverage while preserving the TSFM's accuracy. Our results suggest that TSFM benchmarks should incorporate regime-aware evaluation to surface failures that aggregate metrics hide.

Yingshuo Wang, Xian Sun, Lingdong Kong +4

University of California, Berkeley, CA, USA · Duke University, Durham, NC, USA · National University of Singapore, Singapore +3

Time Series ForecastingForecasting BenchmarksTraffic ForecastingTime-Series Foundation ModelsProbabilistic Time Series ForecastingRegression Prediction Intervals
AskPDF
Jun 15, 2026

TimeVista: Exploring and Exploiting Vision-Language Models as Judges for Time Series Forecasting

High-quality time series forecasting is pivotal for real-world decision-making. However, traditional point-wise metrics often fail to reveal complex temporal patterns and align poorly with human intuitive preferences. While the ''LLM-as-a-Judge'' paradigm has revolutionized text evaluation by providing flexible, human-aligned judgment, its application to time series remains largely unexplored. In this paper, we leverage Vision-Language Models (VLMs) as judges for time series forecasting, harnessing their ability to comprehend time series plots grounded in textual information. Specifically, we propose a novel framework integrating micro- and macro-level judgments informed by contextual information to evaluate time series forecasting. To this end, we introduce TimeVista, a comprehensive VLM-as-a-Judge benchmark comprising 5563 time series samples paired with detailed evaluation rubrics. Extensive meta-evaluations demonstrate that VLMs are highly reliable judges, achieving significantly higher consistency with human preferences than conventional metrics. Building upon our benchmark, we comprehensively assess recent Time Series Foundation Models (TSFMs) under the VLM-as-a-Judge paradigm. Our results demonstrate that VLMs serve as robust and interpretable judges, providing a comprehensive, human-aligned standard for evaluating time series models.

Zhi Chen, Yuxuan Wang, Jialong Wu +5

School of Software, BNRist, Tsinghua University, Beijing 100084, China

VLM EvaluationForecasting BenchmarksVision-Language Model-as-a-JudgeTime-Series Foundation Models
AskPDF
Jun 12, 2026

A Comparative Study of Deep Learning Architectures for Multi-Horizon Behavioural Forecasting for Mobile Health

Wearable devices and smartphones generate rich behavioural time series that can support proactive health interventions, yet systematic comparisons of modern forecasting architectures for these data are lacking. In particular, it remains unclear how models generalise across populations, how different architectures respond to participant-level fine-tuning and how forecasting accuracy degrades across multi-day horizons. We benchmark six deep learning architectures, two zero-shot Foundation Models (FM) and statistical baselines on three public datasets encompassing over 800 participants, reporting per-feature metrics for step counts, screen time and sleep duration across 1-8 day horizons. We further conduct a per-feature personalisation study across all six architectures and assess FM transferability across dataset sizes and temporal granularities. Our key findings are: (i) no single architecture dominates, PatchTST leads among trained models while the three runners-up (TCN, MLP, Transformer) show no meaningful performance difference; (ii) the FM TimesFM matches or exceeds trained models zero-shot, especially in low-data regimes and (iii) participant-level fine-tuning reduces per-feature RMSE by 16-60%, with sleep benefiting most and step counts least. These results provide practical guidance on architecture selection, FM applicability and personalisation strategies for mobile health forecasting. To the best of our knowledge, this is the first study to jointly evaluate modern deep learning, FMs and personalisation for multi-horizon behavioural forecasting from wearables.

Pavlos Nicolaou, Kleanthis Malialis, Artemis Kontou +1

KIOS Research and Innovation Center of Excellence · Department of Computer Science University of Cyprus, Nicosia, Cyprus

Zero-Shot Time Series ForecastingTime Series ForecastingForecasting BenchmarksTime-Series Foundation Models
AskPDF
Jun 12, 2026

Learning the Context of Errors: Black-Box Online Adaptation of Time Series Foundation Models

The rapid evolution of Time Series Foundation Models (TSFMs) has advanced zero-shot forecasting across diverse domains. Inspired by the current form of Large Language Models, future TSFMs may be offered as commercialized, closed-source API services. However, many existing online adaptation methods still rely on white-box access for parameter fine-tuning or gradient backpropagation. This paradigm mismatch raises a question: In black-box online adaptation for TSFMs, what should we learn? We answer this with an insight: the predictive errors of the base model are conditioned on both the input and output of the base model (i.e., the context of errors). To validate this insight, we propose ORCA (Online Residual Contextual Adaptation). We conduct extensive experiments across 5 state-of-the-art TSFMs and 8 datasets to demonstrate the effectiveness of our approach. Furthermore, through ablation studies, we quantitatively analyze the impact of different adapter learning hypotheses on the final adaptation performance in black-box online adaptation. Code available at https://github.com/Fifthky/ORCA.

Xilin Dai, Yiding Liu, Hongjie Xia +4

Ant International · The Chinese University of Hong Kong

Test-Time AdaptationResidual LearningTime Series ForecastingTime-Series Foundation Models
AskPDF
Jun 11, 2026

Beyond Uniform Tokens: Adaptive Compression for Time Series Language Models

Large language models (LLMs) have enabled time series (TS) analysis by jointly modeling numerical observations and textual context through a shared token interface. However, TS tokens and prompt tokens exhibit fundamentally different information structures, making uniform token processing inefficient. In this paper, we study token efficiency in TS language modeling from an asymmetric-token perspective. We show that TS tokens have highly uneven spectral contributions, where many tokens share redundant frequency patterns while a small subset preserves critical temporal evidence. We also observe that prompt-token influence attenuates with model depth, suggesting that full prompt retention across all layers is unnecessary. Based on these findings, we develop an adaptive token budgeting framework that compresses TS tokens via frequency-domain structure and progressively reduces prompt tokens across layers. Experiments across forecasting, classification, imputation, and anomaly detection demonstrate up to \textit{\textbf{7.68×\times}} inference acceleration and performance gains in 78% of evaluated settings, showing the effectiveness of asymmetric token compression for scalable TS foundation models.

Jialin Gan, Xin Qiu, Guangzhe Chen +1

Zhejiang University · Harbin Institute of Technology · Shandong University

LLM Inference AccelerationMultimodal Token CompressionTime-Series Foundation ModelsTime Series Language Modeling
AskPDF