Multivariate Time Series Forecasting

Overview

The field predicts several changing quantities together, such as electricity demand across regions, weather at multiple stations, or patients’ vital signs, where one variable may provide clues about another. Common approaches include linear and MLP models, recurrent networks, Transformers and state-space models, as well as graph, frequency-based, and decomposition methods; newer work also explores probabilistic generation, foundation models, and irregularly sampled data. Models are commonly compared on benchmarks such as ETT, Electricity, Traffic, Weather, and GIFT-Eval, with growing attention to long horizons, uncertainty, and transfer across datasets. A central tension is that cross-variable links and extra context can improve forecasts when informative, but noisy, shifting, or irrelevant relationships can hurt accuracy, so robustness and efficiency matter alongside average error.

Latest papers

325 papers30 papers in the last four weeks, down 45% on the four weeks before. 0.2% of all new papers.

Nov 19, 2026

TRCF: Temporal-Reference Complementary Forecasting for Irregular Multivariate Time Series

Irregular multivariate time series forecasting supports healthcare monitoring, environmental analysis, and activity recognition. Channel-independent (CI) approaches capture each variable's temporal patterns but do not explicitly use observations from other variables. Channel-dependent (CD) modeling exploits relationships among variables, yet asynchronous measurements make these relationships difficult to learn. Incorporating cross-variable information while preserving each variable's irregular history therefore remains a key challenge. We propose Temporal-Reference Complementary Forecasting (TRCF), a framework that augments a compact CI forecaster with a complementary CD branch. ANCHOR aggregates observed values and timestamps at shared temporal locations, retaining observation support to form compact CI features. BRIDGE constructs complementary features through history completion. It first estimates each variable's historical values from its own observations, then uses differences between other variables' observed and estimated values at nearby times to correct missing entries. The completed history preserves observed values and is encoded to supply context alongside the direct CI representation. Finally, the two representations are fused, combined with the query-time embedding, and passed to a shallow multilayer perceptron for forecasting. Experiments on four real-world datasets show that TRCF achieves the lowest mean squared error and mean absolute error in the main benchmark comparison, while reducing measured peak inference memory by 17.28% to 87.98% relative to APN.
Nov 19, 2026

Interpretable Prototype-Conditioned Adaptation for Weather Forecasting

Data-driven weather forecasting requires distinguishing local states and their temporal evolution. However, learned patterns remain implicit in neural forecasters, making their influence difficult to interpret. Failing to distinguish local evolution can lead to similar forecasts for locations that develop differently, increasing prediction error. This motivates explicit references for distinguishing and interpreting local patterns. Prototypes provide explicit pattern references, but sample- or task-level conditioning leaves open how to adapt to distinct locations and variable groups. To deal with this problem, we design ProtoCast, which uses group-specific prototype banks to adapt local features while accounting for cross-variable dependencies. Specifically, (1) we combine each group's historical features and temporal change with forecast context from cross-variable attention for evolution-aware prototype matching. (2) Sparse mixtures of prototype-specific low-rank operators tailor corrections to each group and location. A gated attention block then exchanges the corrected features across groups before prediction. Each group's correction decomposes into explicit prototype contributions before this fusion. (3) We jointly train the forecasting network and operators from scratch and refit each group's prototypes before every training epoch. Slot tracking preserves prototype-operator associations, making each prototype's contribution to local corrections more interpretable. Experiments on GlobalForecast and TyphoonTracking show improved forecasting accuracy, while prototype deletion links local feature contributions to changes in prediction error. This work advances the development of more accurate and interpretable data-driven weather forecasting models. Project page: https://zhixuanli.github.io/projects/li2026protocast
Nov 18, 2026

TRESS: A Fixed-Size History Representation for Irregular Time Series Forecasting

A fixed number of recent observations may span minutes for one variable and days for another. Earlier measurements can still reveal whether the latest value is unusual for that variable. We propose TRESS (Timestamped Recent Events and Statistical Summaries), a forecasting model that retains the latest observations at their original times and summarises the full history of each variable. For a given set of variables and event budget, this representation stays the same size as the record grows. Its query-conditioned event lifting module weights deviations from the latest value according to the age of each observation and the forecast horizon. A channel-specific decoder combines the resulting features with historical statistics and a summary shared across variables to predict a correction to the latest value. Retaining 8 to 16 observations per variable, TRESS records the lowest mean test MSE and MAE among the methods compared on all four benchmarks. Serving 32 successive query times from one encoded history reduces CPU inference time by a factor of 2.12--2.60 across the four datasets. The code is at https://github.com/SSMa913/NICLab-TRESS.
Nov 13, 2026

Which Model, For Which Variable? Per-Variable Forecast Combination in Sparse ICU Time Series

Clinical forecasting papers typically report a single best architecture. We show that on multivariate ICU physiology this question conceals variable-specific differences: no architecture is best on every variable, and which model wins changes from variable to variable. Across five ICU databases (MIMIC-III, MIMIC-IV, eICU, HiRID, and UMM (University Medicine Mannheim), a German single-center ICU) we forecast 94 channels over a 24-hour horizon with a pool of 14 models, and combine them with weights fitted per variable. On test, the combination beats the best single model on all five databases by 6.1-11.0% mean squared error (mean 8.7%). The gain is concentrated where clinical data is thinnest: the sparsest third of channels improves by 11.9% and laboratory values by 7.5%, against 3.1% for the densest third. Rank-based harmonic weighting of the best five models per variable, with no fitted weights at all, recovers about four-fifths of the gain. Extending the pool afterwards with a per-channel gradient-boosted tree, ARIMA and ETS makes the tree the validation-selected best single model on all five databases; per-variable combination still improves on it by 2.9-5.9% (significant on four of five), while equal weighting of the same members does not. As on univariate benchmarks, learned combination beats simple averaging - but only once the weights are constrained. We also report which model to prefer when, and show that the ordering changes with database size.
Nov 12, 2026

Universal Infectious Disease Forecasting with Mantis 2

Public health agencies need to anticipate how outbreaks will unfold, when they will peak, and how long demand on health services will remain elevated. We previously developed a foundation model, Mantis, which was trained entirely on simulated outbreaks---enabling us to generate the diversity and scale of training data needed to support forecasting across diseases. However, our previous work left unresolved when simulation improves predictions and how it should complement observational data. Here, we varied the balance of simulated and observed training data while holding forecasting tasks fixed and varying the available surveillance history. We found that simulation-rich training was particularly valuable with limited local history, and its relative advantage diminished as more observations became available. We also found that simulation-based training reduced exceptionally large forecast errors, suggesting that mechanistic knowledge can help compensate for limited local evidence. Building on these findings, we developed Mantis 2, which combines simulated and observational training to jointly forecast up to six variables sixteen weeks ahead. Across 30 forecasting tasks, Mantis 2 achieved the best aggregate probabilistic accuracy over short, medium, and long horizons among the machine learning, statistical, and baseline models evaluated. It missed roughly 30% fewer outbreak peaks than the strongest comparison model, with successfully anticipated peaks identified more than six weeks in advance on average. We publicly release Mantis 2, enabling public health agencies and researchers to forecast disease outcomes without developing a separate model for each disease or location.
Nov 12, 2026

Time Flies When You Parallelise: Pareto-efficient Time Series Foundation Models with Linear Recurrences

Time series foundation models have demonstrated strong zero-shot forecasting performance, but computational efficiency remains a central architectural challenge. Temporal self-attention incurs quadratic cost in the number of temporal tokens, while nonlinear recurrent state transitions restrict parallel computation along the temporal dimension. We introduce ci-proto, a family of time series foundation models based on Mamba-3, whose linear state recurrences support chunk-wise parallel-in-time computation during training, and inference costs that scale linearly with sequence length. The architecture alternates recurrent temporal processing with cross-variate attention, supporting multivariate probabilistic forecasting with past-only and future-known covariates. Across fev-bench's 100 forecasting tasks, ci-proto XL sets a new state of the art among time series foundation models. The five ci-proto variants also make up the entire Pareto frontier for mean scaled quantile loss and mean absolute scaled error against both parameter count and median runtime.
Nov 11, 2026

PRELUDE: Separating Common Components from Target-Specific Dependencies for Multivariate Time Series Forecasting

Multivariate time series forecasting often improves the prediction of a target by modeling the interactions among variables, and cross-variable modules such as cross-sectional pooling, inter-variable attention, and graph structures are used to construct such interactions. However, by intervening on the cross-variable reading of existing models at inference time, we find that although these models substantially reduce forecasting error through cross-variable interaction, their reading is nearly identical for all targets: the gain appears to come from dependencies among variables but mainly comes from the common component. We term this phenomenon spurious dependency and attribute it to common-component confounding: present in every variable, the common component affects how reading distinguishes sources, so that reading tends to be shared across targets and concentrates on a few similar averages; dependencies thus make up a small share of the read-in content, and a common component composed of several drivers is only partly captured. Theoretical analysis further shows that the common component and dependencies place different requirements on reading and should therefore be handled in different ways. Accordingly, we propose PRELUDE, a separated-reading framework that estimates the common component holistically through cross-sectional pooling and multiple common factors, and reads dependencies for each target via lead-lag relations in the innovation space obtained by prewhitening. Extensive experiments on 16 real-world datasets from four domains show that PRELUDE effectively mitigates spurious dependency and achieves the best overall performance: it attains the best MSE on 23 of the 24 short-horizon and air-quality settings and reduces the average MSE by 6.1% relative to the strongest baseline.
Nov 11, 2026

SkinAdvisor: An AI-Driven Decision Framework for Skin Production Planning via Multi-Modal Transformer Sales Forecasting

Skins, cosmetic in-game items, are a primary revenue stream for modern online games, yet production decisions (which skins to make, when to release, how to price) remain driven by intuition and retrospective analytics. We present SkinAdvisor, an AI-driven decision framework for skin production planning, powered by SkinCast, a deployed multi-modal Transformer forecasting 180-day per-day sales trajectories for unreleased skins. SkinCast couples four encoders: a pretrained Informer for player-preference time series, a pretrained Player-Hero-Skin graph embedder for relational priors, and two lightweight Transformers for skin attributes and release context, fused through a shared backbone with a local-plus-global day-x positional encoding and decoded by an N-layer Informer in a single non-autoregressive pass. SkinAdvisor plugs these forecasts into a serving pipeline (Select -> Fill -> Infer -> Sales -> ROI -> Ranking) that ranks candidate skins by forecast-based ROI and supports multi-candidate comparison. The system has been in production for a full release cycle. Offline experiments show SkinCast reduces RMSE by ~20% over the strongest baseline (Informer) and ~60% over classical methods; stress tests on a 16-core CPU server confirm p99 latency under 8ms and peak throughput above 1100 rps. We report two deployment lessons: order-of-magnitude accuracy suffices for production decisions, and pretrained embeddings can leak temporal information, requiring season-based splitting to prevent.
Nov 10, 2026

AnchorMTS: Multi-View Signal Representation and Forecast-Anchored Fusion for Long-Term Time-Series Forecasting

Long-term time-series forecasters typically optimize a single numerical representation, even though the same history exposes complementary geometry, recurrence, and semantic structure. We propose AnchorMTS, which derives self-aligned visual and textual views from each observed window and uses them only to refine a complete numerical forecast. A trainable evidence path produces a candidate forecast, while a parameter-free output projection enforces an exact per-variable bound on its displacement from the numerical anchor. Across six benchmarks and four horizons, AnchorMTS achieves the best macro MSE/MAE (0.336/0.367) among seven supervised baselines and wins 18 of 24 MSE settings against the cellwise baseline envelope; removing the auxiliary path raises macro MSE to 0.340. The projection leaves 95.8% of candidate refinements unchanged while yielding zero bound violations, showing that complementary multi-view evidence can improve forecasting while its final influence remains explicitly controlled.
Nov 8, 2026

Daily Emergency Call Volume Forecasting using Univariate and Multivariate TimeGPT

This study investigates the potential of TimeGPT, a pretrained foundation model for timeseries, for forecasting daily emergency call volumes. Real-world emergency call data, comprising 2,101 daily observations, are used to evaluate both univariate and multivariate forecasting settings under one-step-ahead and seven-day multi-step-ahead scenarios. The multivariate forecasting incorporates temporal, meteorological, demographic, and socioeconomic variables. A chronological training, validation, and test split is adopted to prevent information leakage, while hyperparameters are selected using the validation set through grid search and early stopping when applicable. Forecasting performance is evaluated using multiple error metrics. Its forecasting performance is compared with several established forecasting approaches, including Seasonal Autoregressive Integrated Moving Average with Exogenous Regressors (SARIMAX), Poisson regression (PR), Negative Binomial regression (NBR), Extreme Gradient Boosting (XGBoost), Multilayer Perceptron (MLP), and Long Short-Term Memory (LSTM). The results show that SARIMAX achieves the best overall performance in the univariate setting. In the multivariate setting, NBR and PR provide best performance. These findings indicate that the large-scale pretraining of TimeGPT do not necessarily translate into superior forecasting accuracy for emergency call volumes. Frugal methods trained solely on the available data remain better for this application.
Nov 7, 2026

TimeHF 2.0: Multimodal, Multivariate, and Multi-Region Collaborative Forecasting for Large-Scale Retail Supply Chains

Large-scale retail supply chains need sales forecasts for specified products, future dates or planning windows, and regions under the conditions available at the forecast origin. Regional sparsity, changing environments, volatile sales, and unfamiliar business situations make these dimensions difficult to model together. We introduce TimeHF 2.0, a multimodal, multivariate, and multi-region collaborative forecasting framework that makes flexibly expressed business knowledge usable in numerical prediction. A coverage-aware directed encoder integrates regional sales and applicable covariates. A semantic alignment module transfers language-model hidden representations of natural-language plans and domain experience into target-specific forecasting context. Learning against sales observations connects these meanings to numerical evidence, allowing business users to supply experience, future plans, and changing circumstances without defining a new numerical feature for each description. Text-conditioned future queries and shared/routed experts adapt prediction to the supplied context. An ordered-distribution head allocates fine resolution to routine fluctuations and coarse resolution to extreme sales movements, while daily/window learning connects forecasts to cumulative planning quantities. Online parallel forecasting at JD yields relative accuracy improvements of 18.25% and 17.94% for national daily and planning-window sales, and 19.44% and 18.99% for DC daily and planning-window sales, over the original production deep learning baseline. Component comparisons, loss-design results, and product-type analyses examine the roles of regional information, covariates, business knowledge, context-dependent processing, and robust planning-oriented learning.
Nov 4, 2026

FaCoDiff: Factor-Correlated Diffusion for Multivariate Probabilistic Forecasting

Multivariate probabilistic forecasting requires modeling cross-variable dependence alongside marginal uncertainty. The challenge is to learn this dependence while controlling marginal noise scales and avoiding dense covariance costs. We propose Factor-Correlated Diffusion (FaCoDiff), which couples a compact conditional statistical estimator with structured denoising. History-conditioned factor loadings use distinct coefficients for forecast-center correction, scale adjustment and noise dependence. Diagonal compensation preserves the estimated marginal noise variances, while low-rank operators enable residual Gaussian likelihood evaluation and noise transport without dense covariance storage or factorization. Factor-derived feature modulation explicitly conditions the denoiser, and a geometry-aware objective accounts for errors after noise transport. The same conditional geometry governs forward perturbations and reverse sampling. Across nine datasets, FaCoDiff achieves the lowest mean variogram score on eight datasets and ranks among the top two on 43 of 54 dataset-metric combinations in the reported comparisons. Matched ablations on Solar and Weather show that factor covariance improves mean Energy and Variogram scores under all four combinations of center and scale correction. Disrupting cross-variable sample pairings while preserving marginal trajectories worsens joint and aggregate scores on both datasets, demonstrating the predictive value of generated cross-variable dependence.
Nov 3, 2026

GlucoAgent: Personalized Glucose Forecasting from Multimodal Personal Context

Continuous glucose monitors, smartwatches, meal logs, and health profiles form a rich multimodal personal context that can significantly enhance glucose forecasting. However, existing methods struggle to effectively utilize these signals to improve glucose prediction because the relevance of different modalities varies drastically across individuals and time. We present GlucoAgent, an LLM-based agentic system that addresses this challenge through dynamic, case-by-case analysis at inference time. For each forecast, GlucoAgent writes and runs code over an individual's multimodal context and returns predictions with a reason and supporting evidence. The generated programs are highly diverse, ranging from retrieving similar past meals to fitting and back-testing physiological and statistical models. On CGMacros, a multimodal glucose dataset, GlucoAgent outperforms time series foundation models on every forecasting horizon, achieving an average RMSE of 22.5 mg/dL compared to 23.5 mg/dL of Chronos-2, the leading multimodal time series foundation model. Furthermore, GlucoAgent is highly effective at leveraging multimodal data. The addition of multimodal data reduces its average RMSE by 1.4 mg/dL (24.0 mg/dL to 22.5 mg/dL), compared to a marginal 0.3 mg/dL (23.8 mg/dL to 23.5 mg/dL) improvement for Chronos-2. This advantage is most pronounced in challenging post-meal windows, where GlucoAgent uses multimodal context to reduce 60-minute forecast RMSE by 4.6 mg/dL (31.0 mg/dL to 26.5 mg/dL), far exceeding the 0.8 mg/dL (31.9 mg/dL to 31.1 mg/dL) reduction achieved by Chronos-2.
Oct 30, 2026

Chronos-2: A foundation model for multivariate time series forecasting

Accurate forecasting with uncertainty quantification is critical in a variety of scientific applications ranging from epidemiology and economics to energy systems and earth sciences. Yet most forecasting models still need to be developed and trained separately for each domain-specific dataset. Time series foundation models (TSFMs) aim to remove this limitation and enable the application of the same model across domains through large-scale pretraining. However, most existing TSFMs treat each time series independently and therefore cannot model interactions among time series and external drivers. Here, we introduce Chronos-2, a foundation model for zero-shot forecasting that models the interactions between multivariate time series and heterogeneous covariates, which commonly arise in scientific applications. The model infers relationships among time series directly from historical context and generates probabilistic forecasts without task-specific treatment. Across various benchmarks, Chronos-2 achieves state-of-the-art accuracy on average by improving skill scores by 5.2 percentage points relative to the strongest baselines and increasing win rates by 10 percentage points. Chronos-2 is also computationally efficient, generating forecasts for 100 time series in under one second on a single mid-range GPU, 50x and 1000x faster end-to-end than the best task-specific point and probabilistic forecasters, respectively. In addition, we demonstrate its effectiveness in diverse scientific settings -- including infectious-disease forecasting, macroeconomic modeling, carbon-flux prediction, and runoff simulation -- where the model matches or surpasses specialized methods developed for each domain. These results show that a single pretrained model can capture structure shared across temporal systems.
Oct 29, 2026

IMPACT: Inverter-Informed Multimodal Learning for Photovoltaic Generation Forecasting

This work develops a physics-informed multimodal deep learning framework for 10- to 110-minute-ahead probabilistic photovoltaic power forecasting. The forecasting model is built on a four-branch architecture that separately encodes plant-level temporal history and inverter-level spatial cloud dynamics through a graph attention encoder with a learned adjacency, known-future solar geometry, and the current meteorological state, fused through gated cross-attention. The geometry branch adds two forward-looking physical signals, spatial cloud heterogeneity and inverter ramp-down activity, each empirically weighted toward the horizon where it is most predictive. The decoder anchors its prediction to a smart persistence baseline, learning a horizon-conditioned correction, and the resulting quantile forecasts are calibrated online through a kernel-weighted adaptive conformal calibration step. The proposed model outperforms all 14 baselines, achieving a forecast skill score (FSS) of 0.2950, 0.099 above the next-best model. A branch-composition ablation shows that every branch contributes positively and the model retains substantial skill in challenging overcast and variable sky conditions (FSS 0.198 and 0.255).
Oct 29, 2026

Multistep and Multivariate Time Series Explainability with GradientSHAP: A Wind Power Case Study

As the effects of climate change become increasingly apparent, the demand for renewable energy sources such as wind power continues to grow. However, renewables' variable and intermittent nature presents significant challenges in their integration into energy grids. Artificial intelligence (AI) has emerged as a powerful tool to address these issues. Still, its adoption in the energy sector has been hindered by the opacity of many AI models, which often function as black boxes. This paper introduces a carefully adapted GradientSHAP approach to provide interpretability for multivariate, multistep wind power forecasting -- a largely underexplored area. This capability is critical for day-ahead grid management and, to the best of our knowledge, this is the first study to apply GradientSHAP in the context of wind power forecasting. To address the inherent dimensionality, we developed novel visualizations that deliver both local and global explanations, uncovering intricate relationships between environmental factors, site-specific conditions, and temporal dynamics. While GradientSHAP is not an out-of-the-box solution, our findings demonstrate that, with thoughtful handling of SHAP values and domain expertise, it can offer valuable insights into model behaviour, supporting more informed and trustworthy decision-making. Nevertheless, its complexity poses challenges for practical implementation. Future research should focus on streamlining these interpretability methods to make them more actionable for routine deployment in critical energy applications.
Oct 29, 2026

Multi-output LSTM soft sensors for industrial anaerobic co-digestion using LSTM-beta-VAE generative data augmentation

Anaerobic digestion (AD) requires close monitoring of key process variables, including pH, the ratio of volatile organic acids to alkaline buffer capacity and biogas production, to maintain biological stability and prevent process failure. While mechanistic frameworks such as the Anaerobic Digestion Model No. 1 are highly parameterised, computationally expensive, and difficult to calibrate for real-time applications, data-driven Long Short-Term Memory (LSTM) networks offer a potentially more adaptable alternative. However, current data-driven approaches in AD are predominantly limited to single-output architectures that focus solely on production yields, as opposed to simultaneous prediction of vital stability indicators. Furthermore, industrial AD datasets are typically sparse and skewed toward steady-state operations. Baseline evaluations demonstrated this scarcity prevents standard algorithms (Random Forest, XGBoost) and unaugmented LSTMs from recognising the transition to unstable operations, resulting in poor estimation of stability indicators. To overcome these challenges, this study proposes a novel generative data augmentation framework using an LSTM-beta-Variational Autoencoder coupled with a multi-output LSTM (MO-LSTM) soft sensor. By synthesising physically valid sequences of these transitions to unstable operations from one year of full-scale plant data, the method safely populates sparse regions of the feature space. Trained on this augmented dataset, the MO-LSTM achieved robust simultaneous estimation across all targets. This approach mitigates data sparsity, providing a basis for hybrid mechanistic-data-driven modelling and early-warning soft sensors in industrial bioprocesses.
Oct 27, 2026

Self-Supervised Latent Action-Conditioned World Modeling for Time Series

Time-series data play an important role in various tasks, such as weather forecasting, web traffic analysis, and speech recognition. Recently, pioneering studies have increasingly adopted Joint-Embedding Predictive Architecture (JEPA) based encoders to learn time-series representations through latent-space prediction. However, they often overlook the underlying factors governing transitions between time-series observations. In this work, we hypothesize that explicitly modeling the information behind changes in time series can facilitate time-series modeling. Building on this hypothesis, we propose ACTS-WM, a self-supervised latent action-conditioned world model framework for time-series analysis. First, we introduce a latent action modeling approach that infers the underlying information behind time-series transitions as latent actions, without requiring explicit action annotations. We then develop a JEPA-based encoder and an action-conditioned world model to predict target time-series representations conditioned on the learned latent actions and task information. We evaluate ACTS-WM across 4 representative tasks on 22 datasets from diverse domains, covering univariate and multivariate forecasting and classification. Comprehensive experiments demonstrate that ACTS-WM can improve downstream performance over pretrained JEPA-based encoders by learning complementary representations.
Oct 27, 2026

Pneuma: A Large-Scale Real-World Time Series Benchmark for Commercial Aircraft Predictive Maintenance

Predictive maintenance is vital for commercial aviation, yet progress remains hindered by the lack of public, large-scale real-world datasets. As a result, most methods are developed and evaluated on proprietary data, limiting reproducibility. We introduce Pneuma, the first publicly available large-scale benchmark for predictive maintenance using onboard time series from in-service commercial aircraft. Built around bleed air systems, Pneuma contains over 920 million multivariate time steps across four aircraft types and 9 verified fault scenarios, directly aligned with real maintenance logs. The dataset exhibits key real-world challenges, including substantial class imbalance, subtle fault evolution patterns, and significant variance across aircraft configurations. We structure the benchmark around three tasks: multivariate forecasting, supervised fault classification, and unsupervised anomaly detection, with labels derived from actual maintenance records. Under unified settings, we evaluate over 25 models from four methodological families on 9 carefully curated subsets. The results reveal that even strong contemporary models struggle with subtle fault signatures. Further analyses show consistent gains from additional in-context examples and multivariate inference, while forecasting quality is strongly associated with anomaly detection performance. Together, these findings provide practical insights into effectively modeling complex real-world aviation time series. We hope Pneuma will serve as a rigorous and reproducible foundation for advancing data-driven predictive maintenance toward real-world deployment in commercial aviation.
Oct 27, 2026

RankFormer: Rethinking Time Series Transformers through Representation Capacity Analysis and Progressive Decoding

Multivariate time series forecasting plays a critical role in Web and cyber-physical systems, where large-scale services and IoT infrastructures generate complex temporal data. Transformer-based models have achieved strong empirical performance in this domain, yet the principles governing the expressive capacity of their learned representations remain insufficiently understood. Moreover, many existing models rely on simplified decoding strategies, including channel-independent modeling and direct projection heads, which limit their ability to capture complex multivariate dynamics. To address these challenges, we propose RankFormer, a novel encoder-decoder architecture for multivariate time series forecasting. We establish a rank-based analysis framework to investigate how tokenization, embedding, and attention designs affect the representation capacity of time series Transformers. Our analysis reveals that patchification increases the potential representation capacity by aggregating multiple temporal observations into each token, while subsequent encoding operations determine how much of this capacity is realized. Guided by these insights, we develop a rank-enhancing encoder with Hourglass Attention to improve rank stability during information interaction. Furthermore, we introduce the Interactive Progressive Decoder (IPD), which improves future trajectory modeling through global-guided cross-channel interaction and progressive refinement. Extensive experiments on real-world long-term forecasting benchmarks demonstrate that RankFormer achieves competitive performance against state-of-the-art methods. Code repository: https://github.com/TangPeiwang/Rankformer.
Oct 26, 2026

SpecLST: Spectral-Enhanced Long-Short Term Spatio-Temporal Multimodal Modeling for Traffic Forecasting

Modeling multi-scale dynamics in urban road networks is essential for intelligent transportation systems but is often hindered by the computational cost of long-range historical context and the challenge of fusing heterogeneous modalities. Existing spatio-temporal frameworks face a trade-off between sequence length and memory overhead, while frequently neglecting the transient effects of exogenous factors such as road incidents and weather. To address these limitations, we propose SpecLST, a frequency-enhanced long-short-term spatio-temporal multimodal framework. SpecLST leverages a fast Fourier transform-based frequency-domain representation module to efficiently encode multi-week historical dependencies, bypassing the memory bottlenecks of standard attention mechanisms over raw long sequences. Heterogeneous context is integrated through attention-based fusion, followed by a sparse Mixture-of-Experts backbone with graph augmentation for spatio-temporal representation learning. Additionally, a frequency-enhanced residual head isolates high-frequency transients, improving sensitivity to abrupt traffic anomalies. At the 60-minute horizon, SpecLST achieves mean relative error reductions of 14.10% in MAE, 10.35% in RMSE, and 15.78% in MAPE across eight neural forecasting baselines and four datasets, with the dataset- and metric-specific average reductions ranging from 5.63% to 22.21%.
Oct 26, 2026

STeP-TS: Shared Temporal Filters with Pruning for Time Series

Multivariate time series forecasting requires capturing temporal dependencies across multiple scales while accounting for both shared and variable-specific dynamics. Compact forecasting models have emerged as an attractive alternative to increasingly large architectures, but preserving strong predictive performance within tight computational and memory budgets remains challenging. We propose a compact one-layer convolutional framework that learns a shared bank of multi-scale temporal filters of each variable. Lightweight variable-specific scalar weights determine the contribution of each temporal component, enabling the model to capture shared temporal structure while adapting to variable-specific dynamics. The learned weights and filter-output energy further provide a natural signal for structured pruning of convolutional filters, reducing computational complexity with minimal degradation in forecasting performance. We additionally introduce an amplitude-adaptive normalization mechanism that preserves variable-dependent temporal amplitudes. Experiments on multiple datasets demonstrate forecasting performance competitive with state-of-the-art methods while requiring substantially fewer parameters and inference FLOPs and achieving low per-sample latency.
Oct 26, 2026

TimeWorld: Towards Action-Conditioned Multimodal World Models for Time Series Forecasting

Time series forecasting supports decision-making in web applications such as online retail and network management, where planned actions can reshape future dynamics. World models provide a natural paradigm for predicting such action-dependent changes beyond extrapolating historical patterns. However, existing time series world models (TSWMs) typically rely on fixed, domain-specific covariate schemas that limit flexible intervention specification, while multimodal forecasters treat text primarily as passive predictive context. To investigate these gaps, we introduce TSWM-Bench, a cross-domain benchmark for multimodal TSWMs spanning seven real-world datasets, with textual interventions grounded in recorded action--outcome data. Our evaluation reveals that conventional multimodal forecasters underperform history-only time series foundation models (TSFMs) despite dataset-specific training, whereas simple text-prefix adaptations improve forecasting across all evaluated TSFM backbones. These findings suggest that pretrained TSFMs encode implicit world knowledge of temporal dynamics, offering a strong foundation for action-conditioned modeling beyond conventional multimodal fusion. Building on this insight, we propose TimeWorld, a plug-in framework that adapts pretrained TSFMs through explicit action-response modeling. Specifically, the Prototype-Guided Latent Modulation (PLM) module grounds textual actions in temporal dynamics by composing representative response prototypes to modulate future representations based on the action and historical patterns. The Action Contrastive Learning (ACL) component strengthens action-specific response modeling by contrasting these updates under alternative interventions sharing the same history, distinguishing action types while preserving relative intensity relationships.
Oct 24, 2026

Learning What to Share: Expert Specialization for Time-Series Forecasting

A central challenge in multivariate forecasting is deciding what to share across channels and where to specialize. Mixture-of-experts models offer flexible sharing, yet it remains unclear how much of their forecasting gains comes from added capacity or expert allocation. Through controlled comparisons across eleven datasets and three backbones, we show that informative channel assignments improve forecasting beyond matched shared capacity and random allocation. On frozen transformer backbones, persistent channel-specific mixtures outperform input-dependent routing on average. To examine when and how much specialization helps, we introduce GalaxyTS, a controlled synthetic dataset with exact shared and channel-specific forecasting references. It reveals how persistent channel mixtures exploit predictive differences concealed by short input windows and measures gains over matched shared corrections. These insights motivate Persistent Closed-Form Routing (PCR), a plug-and-play method that alternates exact conditional estimation of channel-specific mixture weights with gradient-based training of low-rank residual experts around a frozen pretrained forecaster. Averaged over four forecasting horizons, PCR-K4 achieves dataset-balanced mean squared error reductions of 3.86-14.25% relative to the three frozen backbones. In matched comparisons, PCR outperforms competing specialization methods on average while requiring substantially fewer trainable parameters.
Oct 24, 2026

The Future Is Finer: Multivariate Time Series Super-Resolution Forecasting

Web platforms run on multivariate time series, from service telemetry and Web traffic logs to sensor streams served through Web APIs. Yet, retention policies often archive them at coarse granularity to save storage and bandwidth. Decisions such as autoscaling, alerting, and billing operate at finer granularity than existing forecasters reach, since these models predict at the resolution of their input. We therefore introduce Multivariate Time Series Super-Resolution Forecasting (MTS-SRF), which forecasts fine-grained futures from coarse histories, and propose TimeMagnifier to address its three challenges. Fourier Anchor counters data sparsity by fitting each input window to a trend-Fourier structure with sparse cross-variable gating; De-noise Only constrains fine-grained ambiguity by refining along the resolution axis rather than the noise axis, lengthening the grid level by level; and banded DTW Alignment corrects cross-resolution misalignment against the coarse forecast. On the first MTS-SRF benchmark, with ten datasets from five domains, real archived cross-resolution pairs, strengthened baseline adaptations, and five-seed significance tests, TimeMagnifier is best on every dataset, resolution coefficient, and metric against 15 baselines and cuts MSE by 12.3% on average. Its De-noise Only and DTW stages also transfer as a plug-in that lowers the MSE of existing forecasters by 5.1% to 9.0%. Code will be made publicly available.
Oct 23, 2026

Model-agnostic predictability quantification of multivariable time series

Multivariable time series forecasting plays an important role in various domains, where predictions depend on complex interactions among covariates. Forecasting models are commonly evaluated across numerous benchmark datasets. However, forecasting accuracy reflects both model capability and task predictability, making it difficult to characterise the difficulty of a task independently of the model used. Existing predictability measures often fail to capture nonlinear dependencies or are limited to univariate series. In this work, we propose Multivariable Predictability Score (MAPS), a model-agnostic metric for measuring the intrinsic predictability of multivariable time series forecasting tasks. MAPS uses covariate information to assess predictability across different lookback windows and forecasting horizons, and provides a quantitative assessment of the predictive information available for forecasting. We evaluate MAPS across synthetic and real-world forecasting datasets against 6 baseline predictability measures. The former confirms that our method closely aligns with the expected reference predictability (r=0.963). Empirical results further corroborate that MAPS yields more reliable projections in the majority of experimental configurations.
Oct 23, 2026

DBCM: Dual-Branch Calibration Module for Test-Time Adaptation in Time Series Forecasting

Non-stationarity induces test-time distribution shifts in time series forecasting (TSF), resulting in forecast residuals between predictions and the corresponding ground truth. Recent works on test-time adaptation for TSF address this by introducing lightweight calibration modules around frozen forecasters, updated using observations that become incrementally available at test time. Existing approaches typically employ channel-wise adapters, implicitly assuming that forecast residuals are inherently channel-specific. However, we observe that forecast residuals often exhibit substantial shared structure across channels, suggesting that fully independent channel-wise parameterization may be redundant. Motivated by this observation, we propose the Dual-Branch Calibration Module (DBCM), which shares adaptation capacity across channels through a shared adapter while retaining limited channel-specific flexibility through a low-rank channel-wise adapter, further enhanced by channel mixing and nonlinear gated modulation. Extensive experiments show that DBCM consistently outperforms prior methods across diverse datasets, horizons, and backbones.
Oct 21, 2026

Local and Global Recursive Ridge Regression for Online Residual Correction of Frozen Multivariate Forecasters under Label Delay

A frozen multi-horizon forecaster can be corrected online from its own residuals. However, under label delay the target of a block arrives only after the whole horizon has passed, and the corrector's retained state grows with the number of channels. Aiming to combine a small retained state with a large error reduction, we propose DRiC (DCT Ridge Corrector), which fits a ridge regression of the leading discrete cosine transform (DCT) coefficients of the next residual block on those of the frozen forecast and of the latest input block, with sufficient statistics updated recursively. Its local variant, DRiC-L, keeps one such regression per channel; its global variant, DRiC-G, pools all channels into one regression, whose statistics do not depend on the channel count. A guard tracks a running scale of the frozen forecast's residual for each channel; it skips updates on blocks far outside that scale and clips the issued correction. We evaluate on seven datasets (four ETT series, Weather with its missing-value codes filled, Electricity, and Traffic) with DLinear, PatchTST, and iTransformer backbones, against 10 naive, gradient-trained, and closed-form methods. DRiC-L with eight DCT coefficients (DRiC-L8) reduces the mean squared error (MSE) by 14.55% on average over 126 conditions, against 12.98% for ELF, the most accurate comparator, while retaining 15-17 times less state, although ELF is more accurate on Traffic. DRiC-G retains 14.6 kB on the 321-channel Electricity data and 18.9 kB on the 862-channel Traffic data and is the most accurate method at or below its state on both. However, 5 to 7 of the 10 comparators, all with at least 10 times its state, are more accurate there. On the unfilled Weather file, DRiC-L8 without the guard has on average 8.0 times the frozen forecast's MSE, whereas with the guard it reduces the MSE by 7.94%. Code: https://github.com/keiotakmin/dric.
Oct 20, 2026

Model- and Layer-Level Closed-Loop Forecasting with SSM-Based Spiking Neural Networks

Deep State-Space Models (Deep SSMs) have shown promising performance and computational benefits in processing of time-series data with complex temporal dependencies. Spiking neural networks (SNNs) constitute a biologically inspired class of deep SSMs, where computing blocks communicate through spikes, discrete single-bit events rather than continuous activation functions. A particularly important task in time-series processing is forecasting, i.e. predicting future values of a sequence from past observations alone. However, how to best perform forecasting with SNNs is an open question, where the standard autoregressive nature of the data processing with SNNs requires values that are not available during the forecasting phase. In this article, we address this challenge. We explore two closed-loop forecasting strategies, in which the network's own generated values are fed back into the network as if they were observed past values: (i) model-level and (ii) layer-level closed-loop forecasting. We evaluate these approaches on the ETT-small datasets, a standard benchmark for time-series forecasting, under both spike-based and continuous activation functions. We compare the proposed closed-loop approaches against state-of-the-art methods such as SpaceTime, as well as the zero-masking baseline in S4. Both of the proposed approaches perform comparably to or better than zero-masking with S4, and in most cases match SpaceTime. These findings highlight the trade-off between continuous and low-bit quantized activations, and demonstrate that the proposed Deep SSM architectures provide a competitive framework for forecasting.
Oct 20, 2026

Training-Free Continual Learning for Multimodal Forecasting via Prompt Evolution

Adapting a forecasting system to a changing world classically means retraining. We ask whether the task of continually learning regimes for time series forecasting can be represented by a piece of text: a guidance block, evolved by outcome-driven reflection and used in a frozen LLM forecaster's prompt. On a refreshed multimodal benchmark (weekly search indices, daily currencies, daily commodities, each window paired with web-retrieved news), we run GEPA-style prompt evolution under strict contamination control to prevent the data leakage common in timeseries benchmarks: the forecaster's knowledge cutoff predates every evaluated window. A 900-word evolved guidance carried by Llama-3.3-70B beats TimeSeries Foundation Models (TSFMs) on held-out data (GM MASE 0.776 vs. 0.898 for TabPFN-TS-3), transfers to more recent models without measurable loss, and costs dollars rather than GPU-days to update. We characterize the loop: out-of-loop gains concentrate in the first reflection, in-loop improvements overstate out-of-loop gains 2-3x unless an untouched monitor arbitrates, and error-only objectives silently suppress the text modality. We provide two extensions. First, compiling the guidance into executable code with a TSFM as a callable tool recovers most of the gain deterministically. Second, ablations show the advantage widens at short horizons and that removing the news text does not hurt the guided forecaster, consistent with the text's value being distilled into policy during learning. We argue that continual prompt evolution is a practical, training-free alternative to retraining for multimodal forecasting.