Transformer-based models have gained increasing attention in time series research, driving interest in Large Language Models (LLMs) and foundation models for time series analysis. As the field moves toward multi-modality, Large Vision Models (LVMs) are emerging as a promising direction. In the past, the effectiveness of Transformer and LLMs in time series has been debated. When it comes to LVMs, a similar question arises: are LVMs truely useful for time series analysis? To address it, we design and conduct the first principled study involving 4 LVMs, 8 imaging methods, 18 datasets and 26 baselines across both high-level (classification) and low-level (forecasting) tasks, with extensive ablation analysis. Our findings indicate LVMs are indeed useful for time series classification but face challenges in forecasting. Although effective, the contemporary best LVM forecasters are limited to specific types of LVMs and imaging methods, exhibit a bias toward forecasting periods, and have limited ability to utilize long look-back windows. We hope our findings could serve as a cornerstone for future research on LVM- and multimodal-based solutions to different time series tasks.
The paper introduces a novel conditional independence (CI) based method for linear and nonlinear, lagged and contemporaneous causal discovery from observational time series in the causally sufficient case. Existing CI-based methods such as the PC algorithm and also common methods from other frameworks suffer from low recall and partially inflated false positives for strong autocorrelation which is an ubiquitous challenge in time series. The novel method, PCMCI$^+$, extends PCMCI [Runge et al., 2019b] to include discovery of contemporaneous links. PCMCI$^+$ improves the reliability of CI tests by optimizing the choice of conditioning sets and even benefits from autocorrelation. The method is order-independent and consistent in the oracle case. A broad range of numerical experiments demonstrates that PCMCI$^+$ has higher adjacency detection power and especially more contemporaneous orientation recall compared to other methods while better controlling false positives. Optimized conditioning sets also lead to much shorter runtimes than the PC algorithm. PCMCI$^+$ can be of considerable use in many real world application scenarios where often time resolutions are too coarse to resolve time delays and strong autocorrelation is present.
Functional differentiation in the brain emerges as distinct regions specialize and is key to understanding brain function as a complex system. Previous research has modeled this process using artificial neural networks with specific constraints. Here, we propose a novel approach that induces functional differentiation in recurrent neural networks by minimizing mutual information between neural subgroups via mutual information neural estimation. We apply our method to a 2-bit working memory task and a chaotic signal separation task involving Lorenz and R\"ossler time series. Analysis of network performance, correlation patterns, and weight matrices reveals that mutual information minimization yields high task performance alongside clear functional modularity and moderate structural modularity. Importantly, our results show that functional differentiation, which is measured through correlation structures, emerges earlier than structural modularity defined by synaptic weights. This suggests that functional specialization precedes and probably drives structural reorganization within developing neural networks. Our findings provide new insights into how information-theoretic principles may govern the emergence of specialized functions and modular structures during artificial and biological brain development.
Fault diagnosis in Cyber-Physical Systems (CPSs) is essential for ensuring system dependability and operational efficiency by accurately detecting anomalies and identifying their root causes. However, the manual modeling of faulty behaviors often demands extensive domain expertise and produces models that are complex, error-prone, and difficult to interpret. To address this challenge, we present a novel unsupervised fault diagnosis methodology that integrates collective anomaly detection in multivariate time series, process mining, and stochastic simulation. Initially, collective anomalies are detected from low-level sensor data using multivariate time-series analysis. These anomalies are then transformed into structured event logs, enabling the discovery of interpretable process models through process mining. By incorporating timing distributions into the extracted Petri nets, the approach supports stochastic simulation of faulty behaviors, thereby enhancing root cause analysis and behavioral understanding. The methodology is validated using the Robotic Arm Dataset (RoAD), a widely recognized benchmark in smart manufacturing. Experimental results demonstrate its effectiveness in modeling, simulating, and classifying faulty behaviors in CPSs. This enables the creation of comprehensive fault dictionaries that support predictive maintenance and the development of digital twins for industrial environments.
Large Language Models (LLMs) have been extensively applied in time series analysis. Yet, their utility in the few-shot classification (i.e., a crucial training scenario due to the limited training data available in industrial applications) concerning multivariate time series data remains underexplored. We aim to leverage the extensive pre-trained knowledge in LLMs to overcome the data scarcity problem within multivariate time series. Specifically, we propose LLMFew, an LLM-enhanced framework to investigate the feasibility and capacity of LLMs for few-shot multivariate time series classification. This model introduces a Patch-wise Temporal Convolution Encoder (PTCEnc) to align time series data with the textual embedding input of LLMs. We further fine-tune the pre-trained LLM decoder with Low-rank Adaptations (LoRA) to enhance its feature representation learning ability in time series data. Experimental results show that our model outperformed state-of-the-art baselines by a large margin, achieving 125.2% and 50.2% improvement in classification accuracy on Handwriting and EthanolConcentration datasets, respectively. Moreover, our experimental results demonstrate that LLM-based methods perform well across a variety of datasets in few-shot MTSC, delivering reliable results compared to traditional models. This success paves the way for their deployment in industrial environments where data are limited.
The long horizon forecasting (LHF) problem has come up in the time series literature for over the last 35 years or so. This review covers aspects of LHF in this period and how deep learning has incorporated variants of trend, seasonality, fourier and wavelet transforms, misspecification bias reduction and bandpass filters while contributing using convolutions, residual connections, sparsity reduction, strided convolutions, attention masks, SSMs, normalization methods, low-rank approximations and gating mechanisms. We highlight time series decomposition techniques, input data preprocessing and dataset windowing schemes that improve performance. Multi-layer perceptron models, recurrent neural network hybrids, self-attention models that improve and/or address the performances of the LHF problem are described, with an emphasis on the feature space construction. Ablation studies are conducted over the ETTm2 dataset in the multivariate and univariate high useful load (HUFL) forecasting contexts, evaluated over the last 4 months of the dataset. The heatmaps of MSE averages per time step over test set series in the horizon show that there is a steady increase in the error proportionate to its length except with xLSTM and Triformer models and motivate LHF as an error propagation problem. The trained models are available here: https://bit.ly/LHFModelZoo
Time series analysis is pivotal in domains like financial forecasting and biomedical monitoring, yet traditional methods are constrained by limited nonlinear feature representation and long-term dependency capture. The emergence of Large Language Models (LLMs) offers transformative potential by leveraging their cross-modal knowledge integration and inherent attention mechanisms for time series analysis. However, the development of general-purpose LLMs for time series from scratch is still hindered by data diversity, annotation scarcity, and computational requirements. This paper presents a systematic review of pre-trained LLM-driven time series analysis, focusing on enabling techniques, potential applications, and open challenges. First, it establishes an evolutionary roadmap of AI-driven time series analysis, from the early machine learning era, through the emerging LLM-driven paradigm, to the development of native temporal foundation models. Second, it organizes and systematizes the technical landscape of LLM-driven time series analysis from a workflow perspective, covering LLMs' input, optimization, and lightweight stages. Finally, it critically examines novel real-world applications and highlights key open challenges that can guide future research and innovation. The work not only provides valuable insights into current advances but also outlines promising directions for future development. It serves as a foundational reference for both academic and industrial researchers, paving the way for the development of more efficient, generalizable, and interpretable systems of LLM-driven time series analysis.
Time series data in real-world applications such as healthcare, climate modeling, and finance are often irregular, multimodal, and messy, with varying sampling rates, asynchronous modalities, and pervasive missingness. However, existing benchmarks typically assume clean, regularly sampled, unimodal data, creating a significant gap between research and real-world deployment. We introduce Time-IMM, a dataset specifically designed to capture cause-driven irregularity in multimodal multivariate time series. Time-IMM represents nine distinct types of time series irregularity, categorized into trigger-based, constraint-based, and artifact-based mechanisms. Complementing the dataset, we introduce IMM-TSF, a benchmark library for forecasting on irregular multimodal time series, enabling asynchronous integration and realistic evaluation. IMM-TSF includes specialized fusion modules, including a timestamp-to-text fusion module and a multimodality fusion module, which support both recency-aware averaging and attention-based integration strategies. Empirical results demonstrate that explicitly modeling multimodality on irregular time series data leads to substantial gains in forecasting performance. Time-IMM and IMM-TSF provide a foundation for advancing time series analysis under real-world conditions. The dataset is publicly available at https://www.kaggle.com/datasets/blacksnail789521/time-imm/data, and the benchmark library can be accessed at https://anonymous.4open.science/r/IMMTSF_NeurIPS2025.
While adversarial robustness and generalization have individually received substantial attention in the recent literature on quantum machine learning, their interplay is much less explored. In this chapter, we address this interplay for variational quantum models, which were recently proposed as function approximators in supervised learning. We discuss recent results quantifying both robustness and generalization via Lipschitz bounds, which explicitly depend on model parameters. Thus, they give rise to a regularization-based training approach for robust and generalizable quantum models, highlighting the importance of trainable data encoding strategies. The practical implications of the theoretical results are demonstrated with an application to time series analysis.
Time series modeling and analysis have become critical in various domains. Conventional methods such as RNNs and Transformers, while effective for discrete-time and regularly sampled data, face significant challenges in capturing the continuous dynamics and irregular sampling patterns inherent in real-world scenarios. Neural Differential Equations (NDEs) represent a paradigm shift by combining the flexibility of neural networks with the mathematical rigor of differential equations. This paper presents a comprehensive review of NDE-based methods for time series analysis, including neural ordinary differential equations, neural controlled differential equations, and neural stochastic differential equations. We provide a detailed discussion of their mathematical formulations, numerical methods, and applications, highlighting their ability to model continuous-time dynamics. Furthermore, we address key challenges and future research directions. This survey serves as a foundation for researchers and practitioners seeking to leverage NDEs for advanced time series analysis.
Early and accurate detection of anomalies in time series data is critical, given the significant risks associated with false or missed detections. While MLP-based mixer models have shown promise in time series analysis, they lack a causality mechanism to preserve temporal dependencies inherent in the system. Moreover, real-world multivariate time series often contain numerous channels with diverse inter-channel correlations. A single embedding mechanism for all channels does not effectively capture these complex relationships. To address these challenges, we propose a novel cluster-aware causal mixer to effectively detect anomalies in multivariate time series. Our model groups channels into clusters based on their correlations, with each cluster processed through a dedicated embedding layer. In addition, we introduce a causal mixer in our model, which mixes the information while maintaining causality. Furthermore, we present an anomaly detection framework that accumulates the anomaly evidence over time to prevent false positives due to nominal outliers. Our proposed model operates in an online fashion, making it suitable for real-time time-series anomaly detection tasks. Experimental evaluations across six public benchmark datasets demonstrate that our model consistently achieves superior F1 scores.
This paper introduces a dual-layer framework for network operator-side quality of experience (QoE) assessment that integrates both objective network modeling and subjective user perception extracted from live-streaming platforms. On the objective side, we develop a machine learning model trained on mean opinion scores (MOS) computed via the ITU-T P.1203 reference implementation, allowing accurate prediction of user-perceived video quality using only network parameters such as packet loss, delay, jitter, and throughput without reliance on video content or client-side instrumentation. On the subjective side, we present a semantic filtering and scoring pipeline that processes user comments from live streams to extract performance-related feedback. A large language model is used to assign scalar MOS scores to filtered comments in a deterministic and reproducible manner. To support scalable and interpretable analysis, we construct a labeled dataset of 47,894 live-stream comments, of which about 34,000 are identified as QoE-relevant through multi-layer semantic filtering. Each comment is enriched with simulated Internet Service Provider attribution and temporally aligned using synthetic timestamps in 5-min intervals. The resulting dataset enables operator-level aggregation and time-series analysis of user-perceived quality. A delta MOS metric is proposed to measure each Internet service provider's deviation from platform-wide sentiment, allowing detection of localized degradations even in the absence of direct network telemetry. A controlled outage simulation confirms the framework's effectiveness in identifying service disruptions through comment-based trends alone. The system provides each operator with its own subjective MOS and the global platform average per interval, enabling real-time interpretation of performance deviations and comparison with objective network-based QoE estimates.
This competition hosted on Kaggle (https://www.kaggle.com/competitions/trojan-horse-hunt-in-space) is the first part of a series of follow-up competitions and hackathons related to the "Assurance for Space Domain AI Applications" project funded by the European Space Agency (https://assurance-ai.space-codev.org/). The competition idea is based on one of the real-life AI security threats identified within the project -- the adversarial poisoning of continuously fine-tuned satellite telemetry forecasting models. The task is to develop methods for finding and reconstructing triggers (trojans) in advanced models for satellite telemetry forecasting used in safety-critical space operations. Participants are provided with 1) a large public dataset of real-life multivariate satellite telemetry (without triggers), 2) a reference model trained on the clean data, 3) a set of poisoned neural hierarchical interpolation (N-HiTS) models for time series forecasting trained on the dataset with injected triggers, and 4) Jupyter notebook with the training pipeline and baseline algorithm (the latter will be published in the last month of the competition). The main task of the competition is to reconstruct a set of 45 triggers (i.e., short multivariate time series segments) injected into the training data of the corresponding set of 45 poisoned models. The exact characteristics (i.e., shape, amplitude, and duration) of these triggers must be identified by participants. The popular Neural Cleanse method is adopted as a baseline, but it is not designed for time series analysis and new approaches are necessary for the task. The impact of the competition is not limited to the space domain, but also to many other safety-critical applications of advanced time series analysis where model poisoning may lead to serious consequences.
Fast and scalable alignment of time series is a fundamental challenge in many domains. The standard solution, Dynamic Time Warping (DTW), struggles with poor scalability and sensitivity to noise. We introduce TimePoint, a self-supervised method that dramatically accelerates DTW-based alignment while typically improving alignment accuracy by learning keypoints and descriptors from synthetic data. Inspired by 2D keypoint detection but carefully adapted to the unique challenges of 1D signals, TimePoint leverages efficient 1D diffeomorphisms, which effectively model nonlinear time warping, to generate realistic training data. This approach, along with fully convolutional and wavelet convolutional architectures, enables the extraction of informative keypoints and descriptors. Applying DTW to these sparse representations yield major speedups and typically higher alignment accuracy than standard DTW applied to the full signals. TimePoint demonstrates strong generalization to real-world time series when trained solely on synthetic data, and further improves with fine-tuning on real data. Extensive experiments demonstrate that TimePoint consistently achieves faster and more accurate alignments than standard DTW, making it a scalable solution for time-series analysis. Our code is available at https://github.com/BGU-CS-VIL/TimePoint
To be fully useful for public health practice, models for epidemic response must be able to do more than predict -- it is also important to incorporate the mechanisms underlying transmission dynamics to enable policymakers and practitioners to be able to evaluate what-if scenarios and intervention options. However, most mechanistic models suffer from uncertainty in both the parameters (e.g., parameter unidentifiability) and the model structure itself, which can hinder both successful parameter estimation and model interpretation. To enable rapid development of interpretable and parsimonious mechanistic models, we use penalized regression and covariate selection methods to integrate parameter identifiability and model selection directly into the parameter estimation procedure for (in this case) traditional ordinary differential equation (ODE) models. For both simulated and real-world epidemiological data, we demonstrate that the LASSO-ODE framework is highly effective in selecting a parsimonious, identifiable model from larger, more realistic but potentially unidentifiable models, from realistically sparse data with only a single measured compartment and multiple latent (unobserved) variables. While we focus on epidemic models in this paper as a case study, these same approaches are applicable to a wide range of application areas that are faced with relatively sparse data but a need for realistic mechanistic models (e.g. mathematical oncology and mathematical biology more broadly). Additionally, the cross-validation techniques designed for time series data introduced in our study can be used across a range of time series analysis and modeling approaches.
In recent years, the rapid advancement and democratization of generative AI models have sparked significant debate over safety, ethical risks, and dual-use concerns, particularly in the context of cybersecurity. While anecdotally known, this paper provides empirical evidence regarding generative AI's association with malicious internet-related activities and cybercrime by examining the phenomenon through psychological frameworks of technological amplification and affordance theory. Using a quasi-experimental design with interrupted time series analysis, we analyze two datasets, one general and one cryptocurrency-focused, to empirically assess generative AI's role in cybercrime. The findings contribute to ongoing discussions about AI governance by balancing control and fostering innovation, underscoring the need for strategies to guide policymakers, inform AI developers and cybersecurity professionals, and educate the public to maximize AI's benefits while mitigating its risks.
We study the Functional PCA (FPCA) forecasting method in application to functions of intraday returns on Bitcoin. We show that improved interval forecasts of future return functions are obtained when the conditional heteroscedasticity of return functions is taken into account. The Karhunen-Loeve (KL) dynamic factor model is introduced to bridge the functional and discrete time dynamic models. It offers a convenient framework for functional time series analysis. For intraday forecasting, we introduce a new algorithm based on the FPCA applied by rolling, which can be used for any data observed continuously 24/7. The proposed FPCA forecasting methods are applied to return functions computed from data sampled hourly and at 15-minute intervals. Next, the functional forecasts evaluated at discrete points in time are compared with the forecasts based on other methods, including machine learning and a traditional ARMA model. The proposed FPCA-based methods perform well in terms of forecast accuracy and outperform competitors in terms of directional (sign) of return forecasts at fixed points in time.
Stock price prediction remains a complex and high-stakes task in financial analysis, traditionally addressed using statistical models or, more recently, language models. In this work, we introduce VISTA (Vision-Language Inference for Stock Time-series Analysis), a novel, training-free framework that leverages Vision-Language Models (VLMs) for multi-modal stock forecasting. VISTA prompts a VLM with both textual representations of historical stock prices and their corresponding line charts to predict future price values. By combining numerical and visual modalities in a zero-shot setting and using carefully designed chain-of-thought prompts, VISTA captures complementary patterns that unimodal approaches often miss. We benchmark VISTA against standard baselines, including ARIMA and text-only LLM-based prompting methods. Experimental results show that VISTA outperforms these baselines by up to 89.83%, demonstrating the effectiveness of multi-modal inference for stock time-series analysis and highlighting the potential of VLMs in financial forecasting tasks without requiring task-specific training.
Most existing single-modal time series models rely solely on numerical series, which suffer from the limitations imposed by insufficient information. Recent studies have revealed that multimodal models can address the core issue by integrating textual information. However, these models focus on either historical or future textual information, overlooking the unique contributions each plays in time series forecasting. Besides, these models fail to grasp the intricate relationships between textual and time series data, constrained by their moderate capacity for multimodal comprehension. To tackle these challenges, we propose Dual-Forecaster, a pioneering multimodal time series model that combines both descriptively historical textual information and predictive textual insights, leveraging advanced multimodal comprehension capability empowered by three well-designed cross-modality alignment techniques. Our comprehensive evaluations on fifteen multimodal time series datasets demonstrate that Dual-Forecaster is a distinctly effective multimodal time series model that outperforms or is comparable to other state-of-the-art models, highlighting the superiority of integrating textual information for time series forecasting. This work opens new avenues in the integration of textual information with numerical time series data for multimodal time series analysis.
Time series analysis has found widespread applications in areas such as weather forecasting, anomaly detection, and healthcare. However, real-world sequential data often exhibit a superimposed state of various fluctuation patterns, including hourly, daily, and monthly frequencies. Traditional decomposition techniques struggle to effectively disentangle these multiple fluctuation patterns from the seasonal components, making time series analysis challenging. Surpassing the existing multi-period decoupling paradigms, this paper introduces a novel perspective based on energy distribution within the temporal-spectrum space. By adaptively quantifying observed sequences into continuous frequency band intervals, the proposed approach reconstructs fluctuation patterns across diverse periods without relying on domain-specific prior knowledge. Building upon this innovative strategy, we propose Pets, an enhanced architecture that is adaptable to arbitrary model structures. Pets integrates a Fluctuation Pattern Assisted (FPA) module and a Context-Guided Mixture of Predictors (MoP). The FPA module facilitates information fusion among diverse fluctuation patterns by capturing their dependencies and progressively modeling these patterns as latent representations at each layer. Meanwhile, the MoP module leverages these compound pattern representations to guide and regulate the reconstruction of distinct fluctuations hierarchically. Pets achieves state-of-the-art performance across various tasks, including forecasting, imputation, anomaly detection, and classification, while demonstrating strong generalization and robustness.