Time-Series Foundation Models

Time series foundation models (TSFMs) have recently delivered impressive zero-shot performance across diverse forecasting tasks. However, real-world decision-making frequently relies on irregular multivariate time series (IMTS), where inconsistent inter-observation intervals and asynchronous sampling across variables coexist with informative missingness. Existing TSFMs handle such inputs either through imputation that injects spurious values or through index-based positional encodings that ignore continuous time. There is still a gap in the foundation model that follows the original IMTS patterns. In this paper, we propose a hybrid attention model that learns a unified time-aware patch representation for IMTS forecasting. We first design a time-aware patch encoding that maps a variable number of intra-patch timestamps into a fixed-size embedding, producing a uniform format for irregular patches without resorting to imputation. We then introduce a time bias attention mechanism that calibrates inter-patch temporal misalignment and asynchronous cross-channel dependencies as auxiliary attention offset. Finally, on top of a decoder-only Transformer backbone, we adopt a hybrid causal mask that preserves a bidirectional full view over the historical context while keeping the forecast horizon strictly autoregressive. To support large-scale pretraining under irregular settings, we also curate VersaTSA, an archive of $30$B observations that retains the native sampling sparsity of its sources. Experiments on three IMTS benchmarks and a standard regular-MTS benchmark show that our model achieves state-of-the-art zero-shot performance on IMTS and remains competitive when transferred to regular forecasting.

Zero-shot time-series forecasting (TSF) is often described as forecasting without target-specific parameter updates, but that training-status condition does not specify what evidence the system may use. A frozen language model prompted with serialized values, a time-series model pretrained on broad forecasting corpora, and a retrieval-augmented forecaster may all satisfy the no-update condition while drawing on different transferable evidence. This paper argues that zero-shot TSF should therefore be governed as an evidence-access claim. We propose a source-first taxonomy that separates three primary evidence sources---frozen LLM prior reuse, parametric time-series pretraining, and retrieval-augmented external memory---from the architectures that implement them. After the source is identified, four additional audit questions remain: task interface, forecast object and scoring, prediction-time context, and resource budget. The resulting agenda is to make zero-shot leaderboards auditable by reporting evidence boundaries and interface assumptions alongside scores, so that benchmark progress reflects transferable forecasting capability rather than undisclosed changes in context, memory, or budget.

We investigate whether coupling a time-series foundation model to hydraulic project knowledge improves surrogate forecasting of HEC-RAS water-surface elevation (WSE). We present KG-Chronos-2, which combines a frozen Chronos-2 predictor with exact-state residual decoding, graph-conditioned historical retrieval, and input-aligned correction. We compare the method with persistence, a residual LSTM, project-conditioned recurrent GeoFNO, a hydraulic DCRNN-style model, and frozen Chronos-2. Task-specific fitting uses the 2008 simulation. Evaluation covers 64 fixed 24-hour windows from the 2011 and 2002 simulations at 4,675 cross sections in 71 reaches on a shared geometry. KG-Chronos-2 achieves event-balanced root-mean-square error 0.246970 in native WSE units. It reduces RMSE by 14.13% relative to frozen Chronos-2, 29.38% relative to the hydraulic DCRNN-style model, and 39.54% relative to recurrent GeoFNO. The 95% hierarchical-bootstrap interval for its event-balanced RMSE difference from frozen Chronos-2 is [-0.075177, -0.016317]. KG-Chronos-2 also achieves the lowest active-window and final-lead RMSE among the six completed systems. These results support coupling a frozen temporal predictor to project knowledge for warm-start HEC-RAS forecasting on the fixed benchmark.

Deep learning predictive maintenance models suffer from poor transferability across machines and operating conditions, especially when labelled data are scarce and signals span five orders of magnitude in sampling frequency (1 Hz to ~100 kHz). We propose FreqCondNorm, a Transformer-based architecture that introduces a FiLM-style frequency-conditioned normalization layer to unify heterogeneous time-series within a single model. The architecture is pretrained on five public predictive maintenance datasets (CWRU, MFPT, UOC18, PRONOSTIA, CMAPSS) using masked auto-encoding and contrastive learning with balanced domain sampling. On fault diagnosis, the model achieves 99.2% accuracy on CWRU (+6.4 pp over CNN) and 82.1% zero-shot accuracy on MFPT, demonstrating strong transfer across sampling frequencies. However, the approach does not improve remaining useful life prediction, suggesting a mismatch between pretraining and RUL objectives that warrants future investigation.

Ubiquitous time series data across diverse domains enables critical applications in areas such as transportation systems and power grids. Recently, training foundation models on massive datasets to achieve accurate zero-shot forecasting has emerged as a major research focus. However, current studies predominantly prioritize architectural innovations while insufficiently addressing data diversity, often relying on simple data sampling strategies that fail to manage complex data distributions effectively, leading to inefficient use of training data and suboptimal performance. To address this, we propose QUALS, a large-scale time series corpus equilibrium framework. QUALS significantly enhances data efficiency, i.e., enabling existing models to achieve superior performance using only a small fraction of the original training data. Specifically, QUALS operates through two core mechanisms. First, a pattern quantization framework systematically decodes heterogeneous patterns from mixed corpora via vector quantization and uniform binning. Second, a learnability synchronization framework calibrates sampling weights for heterogeneous patterns, bridging the optimization gap between simple and complex motifs to maximize overall training efficiency. Extensive benchmarks demonstrate that pre-training on QUALS consistently achieves superior zero-shot performance, even under substantially reduced training budgets.

Time-series language models provide a shared natural-language interface across temporal tasks, but plausible text does not guarantee reliable task outputs. Responses may appear reasonable while hallucinating the required object: numerical sequences can violate shape, scale, channel order, or temporal alignment, and textual decisions can fall outside the legal label space. We formulate reliable time-series language modeling, separating task-object reliability from predictive quality. We introduce ExecTS-QA, a contract-grounded benchmark spanning forecasting, imputation, classification, anomaly detection, and waveform analysis. We further propose WaveTLM, a unified compiler-executor model whose task compiler transforms user requests, visible arguments, and wave-grounded evidence into typed task states, while task-native executors construct numerical tensors, legal decisions, or structured records. On ExecTS-QA, a single WaveTLM checkpoint achieves 99.40% contract-valid coverage, compared with 37.83% for the strongest evaluated string-first baseline, while retaining balanced predictive performance across all five task families. Evaluations on SciTS, TSQA, IRTS-ToolBench, and ARFBench provide additional evidence of transfer. The code, construction scripts, and ExecTS-QA dataset will be publicly released upon publication. These results show that task compilation can convert plausible language generation into reliable time-series outputs.

TW3Cast is a time-series forecasting system that reaches position 3 of 130 entries on the GIFT-Eval benchmark by mean MASE rank, as of 2026-09-14. The two entries above it belong to the leaderboard's agentic category, multi-step systems that use agents or language models to reason about, generate or select forecasts. TW3Cast runs no agent and no language model. Its selection is a table computed once on the training split and then frozen, and its experts are public foundation models lightly fine-tuned on those training splits. For each of the 97 dataset, frequency and horizon configurations, the table serves one of four modes: a specialist, which is a LoRA or full fine-tune of Chronos-2, TiRex or Toto whose training data was cleaned and enriched by explicit rules; a quantile blend that contains a specialist; a blend of base models; or a selection tournament played on a backtest carved from the training split. Every decision in the table was taken on that backtest. A specialist is admitted the moment it beats the tournament there, so a candidate costs a few megabytes and minutes of GPU time, and a failed candidate changes nothing. Three guarded mechanisms protect the selection from its own biases: a dual accuracy and calibration criterion, an asymmetric margin against candidates that saw the series during training, and conservative per-window gates. The selection rules themselves were chosen inside a temporal meta-backtest. The best base model served alone reaches a mean MASE rank of 33.8, the tournament served on every configuration reaches 38.0, and the full router reaches 19.4. The routing table, the expert index, the pinned base-model revisions, the submitted score file and the dated snapshot of the public scores are released, and every leaderboard number in this paper regenerates from them by one script.

For distribution system operators, short-term load forecasting (STLF) supports congestion management, voltage control, and asset protection. Most existing approaches focus on overall accuracy across all time steps and neglect performance during high-demand (HD) periods, where larger forecast errors can increase the risk of congestion and voltage violations. In this paper, we study peak-aware STLF across three operator-relevant distribution grid aggregation levels, area codes (AC), secondary substations (SUB), and low-voltage (LV) feeders, using open datasets from the United Kingdom and Switzerland. We compare statistical baselines, machine learning models (LightGBM and XGBoost), and recent time-series foundation models (Chronos Bolt and Chronos-2) under a peak-aware evaluation framework that reports both overall and HD forecasting performance using NMAE and MAPE. The results show that Chronos-2 achieves the best HD performance across all aggregation levels, with HD-NMAE and HD-MAPE of 0.039 and 4.53% at AC, 0.080 and 9.45% at SUB, and 0.138 and 16.14% at LV, while Chronos-Bolt consistently ranks second best. Compared with the gradient boosted ML models, Chronos-2 reduces mean HD-NMAE by about 20-51% across levels while remaining best or near-best on the overall metrics. A quantile analysis of the probabilistic Chronos outputs further identifies aggregation-specific operating points, and runtime measurements indicate that foundation model inference is fast enough for practical deployment. Overall, the findings highlight peak-aware evaluation and aggregation specific quantile selection as a practical pathway toward more operationally relevant STLF in distribution networks.

Earth observation is inherently dynamic, yet temporal information in many foundation models is learned through reconstruction, invariance, or retrospective sequence summarization. SPEAR NeXT is introduced as a compact pixel-wise multimodal spectral temporal foundation model in which temporal self supervision is formulated as past only, multi horizon latent Earth state prediction. Instantaneous states are first encoded by the pretrained SPEAR model from optical, radar, and environmental observations into compact 32 dimensional embeddings. Their temporal evolution is then modeled by a causally masked Trans former that predicts multiple future latent states from pre ceding observations. Relative temporal order is represented using Rotary Position Embeddings, while month and year embeddings encode seasonal phase and interannual con text.

Time-series foundation models have demonstrated strong cross-domain transfer, yet their common architectural assumptions remain poorly aligned with wearable physiological signals, which are multichannel, irregularly sampled, noisy, and governed by coupled continuous-time dynamics spanning distinct spectral scales. We present SOTER, a generative foundation model for wearable physiological time series that unifies cross-channel coupling, spectrum-guided expert specialization, and continuous-time latent evolution within a single pre-training framework. SOTER combines a spatial feature-aware backbone that models inter-signal dependencies, a power spectral density (PSD)-guided mixture-of-experts layer that routes representations to experts associated with fixed spectral bands through an inspectable, non-learned rule, and a neural controlled differential equation decoder that supports prediction and imputation at arbitrary timestamps. We pre-train SOTER on 226 billion time points from five public physiological datasets and evaluate the same pre-trained model across out-of-distribution zero-shot forecasting, frozen-encoder linear-probe classification, and continuous-time imputation on wearable benchmarks. SOTER achieves the best RMSE on 4 of 6 datasets and the best MAE on 5 of 6 in zero-shot forecasting, the highest average Macro-AUROC in classification, and the lowest imputation error on all six datasets at 75% missingness. It further remains robust to additive acquisition noise, matching or surpassing baselines evaluated on clean inputs even under the strongest corruption. These results indicate that domain-specialized foundation models for wearable physiology benefit from jointly modeling channel structure, spectral scale, and continuous-time dynamics.

Pedestrian-count forecasting supports pedestrian-oriented Intelligent Transportation Systems (ITS), including crowd monitoring, pedestrian-traffic staffing and routing, and proactive risk mitigation during surges. Recent time-series foundation models (FMs) report strong zero-shot accuracy on heterogeneous forecasting benchmarks, but it remains unclear whether these gains transfer reliably to pedestrian sensing deployments. We benchmark seven univariate forecasting approaches spanning four paradigms: Seasonal Naive, gradient-boosted trees (LightGBM, CatBoost), deep learning models (N-HiTS, PatchTST), and two pretrained FMs (TimesFM, Chronos-2). Experiments cover two complementary regimes: (i) a five-day special event dataset SAIL2025 at 3-minute resolution with limited in-domain history; and (ii) Melbourne pedestrian sensors as a multi-year hourly dataset (2010--2017) with strong seasonality. We compare the MAE and RMSE results per sensor across datasets and multiple forecast horizons. Results show three consistent findings. First, with limited historical data, Seasonal Naive remains a strong baseline for long-horizon forecasting on high-volume sensors, while trained models can degrade when the next day differs substantially from prior days. Second, boosted trees can be competitive on lower-volume sensors but exhibit higher sensitivity on high-volume sensors under event-driven shift. Third, FMs excel in the seasonal and data-rich regime under long-context configuration. The findings highlight the importance of choosing pedestrian forecasting models based on both the underlying data conditions and the forecasting horizon.

Most time series forecasting benchmarks remain numerical-centric and provide limited support for evaluating contextual information that shapes real-world temporal dynamics. Existing multimodal benchmarks also suffer from limited data and context coverage, fragmented evaluation settings, and overreliance on aggregate evaluation. In this paper, we propose MUSE-Bench, a unified benchmark for multimodal time series forecasting with heterogeneous context. It comprises fourteen datasets across eight domains and six types of context: metadata, events, holidays, news, images, and numerical covariates. We evaluate diverse forecasting paradigms, including statistical, data-specific, foundation, multimodal, and general-purpose LLM forecasting methods under shared non-overlapping forecast windows, common target observations, and consistent point and probabilistic metrics. Extensive experiments yield three main findings. First, numerical time series foundation models dominate the overall ranking, while Aurora, the evaluated multimodal foundation model, trails the leading numerical TSFMs but outperforms all evaluated data-specific models. Second, ablations show that external context improves the four evaluated context-aware models, whereas incorrect or temporally misaligned context degrades performance. Third, general-purpose LLMs perform poorly as direct forecasters, and LLM-guided refinement does not yield consistent improvements. MUSE-Bench enables systematic evaluation of how forecasting models utilize context and provides a foundation for future multimodal forecasting research.

In this report, we release Tabby, a long context probabilistic time series foundation model, together with a complete and open recipe of how it was built. Tabby adopts an encoder-only patch Transformer architecture and concentrates the contributions on the data and the training procedure. The pretraining corpus combines an extended real-world collection, GIFT-Eval-Pretrain+ and BLAST, with synthetic data from KernelSynth and CauKerV2, an online generator that composes temporal dynamics through randomly sampled structural causal models. Training couples a progressive convergence schedule, which yields reusable intermediate checkpoints, with a deep quantile supervision objective for intermediate layers. The resulting 145M parameter backbone supports contexts of up to 8,192 observations and serves forecasting, classification, and anomaly detection, while a prompt-tuning module further improves in-distribution forecasting performance with the pretrained weights frozen. Tabby achieves competitive zero-shot forecasting performance on GIFT-Eval and the out-of-distribution TIME benchmark, while the same pretrained backbone also supports classification on the UCR Archive and zero-shot anomaly detection on TSB-AD-U. We release training pipeline and model as open source at huawei-noah/trustworthyAI.

Encoder-based time series foundation models (TSFMs) typically rely on deep stacks of independently parameterized Transformer layers, where only the final forecast is supervised and intermediate representations have no explicit predictive role. We introduce FlowTSFM, an encoder architecture that interprets depth as a recurrent transport process: a single Transformer block is iteratively applied with shared parameters, while a quantile-flow objective supervises intermediate states along a prescribed trajectory from a prior distribution toward the final forecast. The objective combines pinball forecasting loss with path-level position matching. With only 38.8M parameters, FlowTSFM achieves competitive performance on GIFT-Eval and TIME, remaining within 1.8-4.6% MASE of stronger baselines while using approximately $3\times$ fewer parameters than a 12-layer Chronos-2 model (119.5M). Beyond accuracy, we introduce CosMean, a scale-free diagnostic measuring whether recurrent updates consistently align toward the final prediction. Under a matched intermediate-state probing protocol, FlowTSFM achieves a CosMean score of 0.919 compared with 0.350 for Chronos-2, suggesting that recurrent parameter sharing combined with path supervision is associated with substantially more structured predictive trajectories at a favorable accuracy-efficiency trade-off.

Continuous glucose monitoring (CGM) provides high-frequency measurements of glucose dynamics and enables short-term glucose forecasting for diabetes management. Although time-series foundation models have shown strong general forecasting ability, their effectiveness for CGM prediction and the added value of multimodal dietary context remain unclear. We conduct a comprehensive empirical study using eight public CGM datasets spanning Type 1 diabetes, Type 2 diabetes, and non-diabetes populations. Under a unified protocol across multiple context lengths and prediction horizons, zero-shot foundation models did not consistently outperform strong task-specific baselines such as Elastic Net and PatchTST. In contrast, lightweight fine-tuning substantially improved forecasting performance. For example, fine-tuned Chronos-Bolt reduced RMSE by 6.5%-18.4% in the T1D cohort and by 8.6%-18.2% in the non-diabetes/T2D cohort, with comparable improvements in both in-distribution and out-of-distribution test settings. We further evaluate multimodal dietary context using CGMacros, which provides temporally aligned CGM signals, food images, and macronutrient records. A residual-based fusion framework reduced overall RMSE by approximately 3% and postprandial RMSE by approximately 15% relative to the CGM-only baseline. Moreover, Chronos-based CGM representations were more strongly correlated with observed postprandial glucose increments than representations from LSTM and CatBoost, even after those models incorporated additional dietary modalities, suggesting that pretrained temporal representations better preserve meal-induced excursion patterns. These findings show that foundation models require CGM-specific adaptation for reliable forecasting and that dietary context provides clinically meaningful signals beyond CGM alone, especially during postprandial periods.

Time-series foundation models are evaluated almost exclusively on public archives that predate them, so a strong score cannot be separated from having seen the test set during pretraining. The obvious remedy is a hold-out that postdates the models. We build one: thirteen forecasters -- four classical, three trained per dataset, six pretrained -- on seven groups drawn from five domains, every observation published after the last model was released, and every dataset rebuildable without an API key. Under this protocol pretrained models win 5 of 7 groups, lose one to a Theta baseline, and on daily exchange rates are indistinguishable from a seasonal naive forecast, along with every other method tested. We then ask what separates the wins from the losses, and report a negative result: the two intrinsic properties one would reach for -- seasonal strength and spectral entropy, measured on the input window -- do not account for the pattern, and seasonal strength is if anything negatively associated with the advantage. What does track it is corpus familiarity. Our largest gain (28% lower MASE than the best classical method, on weekly Wikipedia pageviews) falls on Wikipedia pageviews, the domain TimesFM's authors describe as the bulk of its pretraining corpus, at the same granularities and differing only in time window. Within the pretrained family, where every model forecasts identical series so that series difficulty cancels, the TimesFM family outranks the Chronos family by -0.53 ranks on Wikipedia against -0.09 everywhere else (1,500 vs. 754 series, Mann-Whitney p < 1e-5). We conclude that a temporal hold-out removes memorisation of a window but not familiarity with a domain, that benchmarks therefore need domain hold-outs stated relative to disclosed corpora, and that the practitioner's question is less which model is better than whether their domain is one the model was raised on.

Time series foundation models (TSFMs) are increasingly pre-trained on synthetically generated time series trajectories, where the data generating process is known. Current pre-training recipes are based on loss objectives which compare TSFM outputs to realized future values of each trajectory. We instead propose loss objectives which compare TSFM outputs to the conditional forecast distribution of each trajectory, a procedure we call synthetic data distillation (SDD). SDD corresponds to a Rao-Blackwellization of the training objective, in that it leaves the expectation of stochastic gradients unchanged while provably reducing the covariance of the stochastic gradient under the Loewner partial ordering. We empirically validate SDD on a TSFM model family of sizes from $4$M to $2.5$B parameters, and observe faster convergence of validation loss at every model size: on Gaussian Process data, SDD attains or improves upon the Status Quo loss whilst requiring $10\%-40\%$ less training iterations.

Industrial process monitoring is fundamental to the safety and economic performance of modern process plants. Current practice remains a one-task-one-model paradigm that is label-inefficient and prone to degradation under operating drift. Foundation models have reshaped language, vision, and generic time-series forecasting, but it has not been adapted to industrial process monitoring. This setting poses domain-specific challenges, including safety-critical decisions and asymmetric sampling between process variables and laboratory measurements. We propose the industrial process monitoring foundation model (IPM-FM). It first learns general-purpose representations from unlabeled industrial process data through self-supervised pretraining, then adapts to specific monitoring tasks using a small amount of task-labeled data, and finally produces calibrated predictions through an uncertainty-aware prediction head. IPM-FM integrates a self-supervised Informer backbone with a multi-criteria consensus feature selector, a recursive lag-feature regression head, and a calibrated Monte Carlo dropout uncertainty module. On a seven-year hydrotreater dataset for diesel flash-point soft sensing, IPM-FM attains an RMSE of 2.99, $R^2$ of 0.50, and 97% coverage of its 95% predictive interval, outperforming the strongest classical and from-scratch sequence baselines by 8.3% and 14.6% in RMSE respectively, supporting the viability of a unified pretraining--adaptation framework for industrial process monitoring.

This technical report presents EXAONE Forecast for Finance (EXAONE Finance), a financial time series (TS) foundation model (TSFM) tailored to financial forecasting. Recent TSFMs achieve strong zero-shot performance through large-scale pretraining. However, they are primarily developed for general-domain TS and largely rely on self-attention backbones whose computational cost grows quadratically with sequence length and variate count. Moreover, they assume fully observed inputs and are pretrained on corpora that fail to capture the unique dynamics of financial markets. These limitations hinder their applicability to finance, where long, many-channel, intermittently observed panels are common. To address these challenges, EXAONE Finance adopts an attention-free architecture, replacing self-attention with two simple yet effective linear-time operators: 1) a causal 1D convolution for temporal mixing and 2) a group-aware pooling multi-layer perceptron (MLP) for variate mixing. Furthermore, a masked context augmentation exposes the model to contiguous missing spans during training, improving robustness to the missingness pervasive in financial markets. EXAONE Finance is pretrained on a large-scale financial corpus covering not only equities but also foreign exchange, commodities, crypto-assets, fixed income, and macroeconomic indicators. On FinVerse, a financial forecasting benchmark covering diverse asset classes, EXAONE Finance attains state-of-the-art performance, ranking first across all three evaluation tiers---point-forecast accuracy, cross-sectional asset ranking, and portfolio profitability.

Modern power systems are growing increasingly complex as they integrate diverse generation sources to meet rising demand, making accurate load forecasting challenging. Recent advances in time-series foundation models (TSFMs) resulted in promising performance in zero-shot univariate load forecasting tasks. However, real-world load forecasting often involves multiple target variables and requires the integration of exogenous variables, raising important questions about the utility of TSFMs in realistic settings. In this study, we position Chronos-2, a recently developed model by Amazon, as a representative multi-channel TSFM that supports univariate, multivariate, and covariate-informed forecasting, and conduct a systematic investigation of how such models can be used for real-world load forecasting. While prior work has evaluated Chronos-2 on a limited number of energy-related tasks in a zero-shot setting, its performance relative to established task-specific deep learning models and its behavior when adapted using task-specific historical data remains insufficiently understood. In this work, we evaluate Chronos-2 on two real-world utility datasets, ISO New England and ENTSO-E, and benchmark it against widely used task-specific deep learning models. Our results show that Chronos-2 benefits substantially from task-specific fine-tuning and achieves strong short-horizon forecasting performance, but its zero-shot accuracy lags behind task-specific models and its forecasting error grows more rapidly with increasing forecast steps. Overall, this study provides a detailed characterization of the strengths and limitations of TSFMs such as Chronos-2 in grid load forecasting and offers practical insights into how a pretrained TSFM can be effectively adapted for operational load forecasting applications.

We present Cadence, an error-bounded lossy compressor for numeric time series pairing a 330M-parameter time-series foundation model (Google TimesFM-3) with an adaptive arithmetic coder, guaranteeing $|\hat{x}_t-x_t|\leτ$ on every sample. One negative result constrains the design space: for lossless coding a foundation model is worth nothing, because bits saved are logarithmic in predictor accuracy, $Δb=\log_2(\mathrm{MAE_{old}}/\mathrm{MAE_{new}})$. So the $1.51\times$ advantage TimesFM-3 holds over a 32-tap linear predictor buys 0.60 bits of 20.28, a median gain of +0.03%. Error-bounded coding escapes this at one point: once a forecast lands inside the band the residual index is zero and the sample nearly free. Cadence contributes: (1) an adaptive range coder with context-modelled binarization, beating xz/zstd on real indices by 9.7% (15/15) and reversing a finding from a general-purpose back end; (2) a determinism result -- predictions are not bit-identical across batch sizes, and no PyTorch configuration repairs this, forcing group size and execution device into the container format; and (3) domain localization on corpora postdating any plausible training cutoff. On 49 EIA-930 balancing-authority demand series (2026) Cadence gains 13.3% over the best of six classical predictors, and 28.3% on 50 MTA ridership series (2026): 21.4% median over 297 series-tolerance pairs, winning all 297. Against downsampling, what time-series databases deploy for retention, its guaranteed worst-case error is $28$--$56\times$ tighter at equal size. End-to-end, once the context bootstrap is paid for, gains run from 6.8% at six months of hourly data to 15.1% asymptotically. Attempting to falsify the domain claim on SDRBench, theory predicts failure and delivers: -0.8% median, 0 of 27 pairs gaining. Three further negative results and eight retracted claims are reported in full.

Power-outage planning requires scenarios before an event occurs. These scenarios must represent uncertainty in magnitude, timing, and duration while preserving temporal dependence. However, severe events are rare, and data from any single region contain few examples of extreme outage and restoration patterns. To address this challenge, we introduce OutageDiT, a foundation model for generating seven-day outage trajectories at 15-minute resolution, trained on outage and weather records across the United States. Specifically, a condition encoder processes historical context and known future covariates once per forecast, and a shallow flow-matching decoder reuses the resulting horizon-aligned states to sample complete outage trajectories. This enables point forecasting, uncertainty quantification, and conditional scenario generation within one deep generative model. Across outage forecasting benchmarks, OutageDiT improves forecast accuracy and scenario quality over strong baselines and supports zero-shot transfer to held-out regions. Together, these results position conditional outage scenario generation as a bridge from outage forecasting to operational planning under uncertainty.

Designing models that generalize effectively in low- to medium-data regimes remains a primary challenge in medical machine learning, particularly for physiological time-series classification. While tabular foundation models such as TabPFN offer an attractive alternative to conventional fine-tuning through in-context learning, they are not designed to capture the temporal dependencies inherent to physiological signals. ~In this paper, we introduce TSPFN, a foundation model that redesigns TabPFN's architecture for time series data. TSPFN integrates structured temporal representations and positional embeddings to capture intra-sample temporal and channel dependencies. To fully leverage its spatio-temporal design, the model is pretrained on 140,000 real-world physiological time series across multiple medical domains. This yields a unified, generalizable framework capable of learning the specificities of medical time series. Experiments across diverse physiological benchmarks demonstrate that TSPFN consistently outperforms standard tabular baselines and TabPFN, and achieves superior cross-domain generalization compared to specialized deep time-series models. All our experiments, ablation studies, and pre-processing scheme are publicly available at https://github.com/Jeremstym/TSPFN

Foundation models promise accurate forecasts with little or no task-specific training, but whether they can replace models designed specifically for electricity price forecasting remains unclear. We compare nine variants from five foundation model families, evaluated in zero-shot mode, with two state-of-the-art electricity price forecasting benchmarks in Germany, Poland, and Spain over 2021-2025. Their performance is assessed in terms of point and probabilistic forecasting accuracy, as well as economic value in battery energy storage arbitrage. Only the TabPFN models consistently and significantly outperform the benchmarks across all three markets and all statistical measures. However, this statistical dominance does not translate directly into economic dominance: TabPFN performs best under unlimited bids and riskier quantile-based strategies, whereas the Distributional Deep Neural Network benchmark is more profitable when risk tolerance is lower. Thus, foundation models cannot universally replace market-specific models, and their value depends on both model architecture and the decision problem.

Main sequence stars of spectral types late F through M exhibit systematic variability in photometric light curves, particularly when they are young. Rotational modulation of starspots manifests as quasi-sinusoidal variability, which enables the measurement of rotation periods. Variability can also be stochastic, as in stellar flaring. However, since measurements of stochastic processes depend on the time of observation, they are typically noisier. Considering that different manifestations of variability have unique observational nuances, models that naturally unify these are incredibly useful for stellar characterization. Towards this goal, we have developed EncoTESS: a Time Series Foundation Model (TSFM) trained on a subset of TESS 2-min light curves. EncoTESS is specifically designed to handle the observational noise, heteroskedastic measurements, irregular sampling, and large data gaps common to TESS data. It is also ~1% of the size of a typical literature TSFM, so can be run easily on a modern laptop. EncoTESS encodes light curves into a fixed-size latent parameter space, which can be used to infer physical stellar properties and recovers light curve summary statistics well. EncoTESS outperforms rotation period and variability amplitude as age indicators for stars that have not converged onto the slow rotator sequence yet; broadly these include K and M stars less than ~100 Myr, and M stars less than ~1 Gyr. We focus on age inference as an application of EncoTESS in this work, but other downstream tasks such as stellar classification could also be explored. The architecture of EncoTESS enables its future extension to TESS light curves of all cadences, and additional surveys such as Kepler and the upcoming PLATO mission. The core EncoTESS framework and library of encodings produced for the stars used in this work are publicly available at https://github.com/philvanlane/encotess.

Transitioning from bespoke time series models towards time series foundation models changes the relationship of model and application from one-to-one to one-to-many. This shift introduces concentration risk as many, potentially high-risk, forecasting applications are exposed to the same biases and failure modes of a single time series foundation model. At the same time, this centralization allows for economies of scale in model development and validation. In this study we investigate how biases and failure modes of time series foundation models can be identified before deployment. We propose a causal analysis framework to investigate the ability of a time series foundation model to preserve time series patterns. To achieve this, we intervene on parameterized synthetic time series generators and measure the corresponding change in model output under ceteris paribus conditions. We apply our causal analysis framework to Chronos-2 and TimesFM-2.5 and test them across six distinct time series patterns. We find safe configurations for trend and harmonic oscillation patterns. The results also indicate a bias in both models towards overestimating persistence, sudden failures for both models against the regime switch pattern and failure for TimesFM-2.5 against the energy-release pattern. Our review of the original works for both models indicates that the findings might be explained by the data used for pretraining. We conclude our study with suggestions for further model development, recommendations for application-specific model selection, and a discussion of limitations and further research directions.

Time series classification underpins applications in healthcare, sensing, and industrial monitoring. Although time series foundation models support forecasting and transferable representation learning, classification still typically requires fitting a task-specific classifier on each target dataset, while individual channels of multivariate inputs are often encoded independently. We introduce ChorusTIC, a classification-native foundation model for in-context classification across heterogeneous channel configurations without target-task parameter updates. ChorusTIC combines episode-consistent Random Subchannel Slot Concatenation with a shared dual-axis encoder to model temporal and cross-channel interactions and map variable channel configurations into a fixed-width representation independent of the original channel count. It then calibrates feature axes using context-derived distributions and predicts query labels through leakage-protected in-context learning. We pretrain ChorusTIC solely on synthetic labeled episodes comprising context and query sets that share a task background, with classes distinguished by sparse temporal or cross-channel rules. Evaluations on the complete UEA-30 and UCR-128 archives show strong full-context and low-label performance without target-specific classifier fitting.

We present a dynamical-systems based model for resting-state functional magnetic resonance imaging (rs-fMRI), trained on a dataset of roughly 40K rs-fMRI sequences covering a wide variety of public and available-by-permission datasets. While most existing proposals use transformer backbones, we utilize multi-resolution temporal modeling of the dynamics across parcellated brain regions. We show that MnemoDyn is compute efficient and generalizes very well across diverse populations and scanning protocols. When benchmarked against current state-of-the-art transformer-based approaches, MnemoDyn consistently delivers superior reconstruction quality. Overall, we find that with such large-scale pre-training on (non-proprietary) rs-fMRI datasets, we get a highly performant model for various downstream tasks. Our results also provide evidence of the efficacy of the model on small sample size studies which has implications for neuroimaging studies at large where resting state fMRI is a commonly acquired imaging modality.

Industrial monitoring models must detect operationally relevant deviations while satisfying target-specific data, calibration, and resource constraints. Time-series foundation models (TSFMs) promise reusable representations and zero-shot forecasts, yet evidence for their deployment value remains mixed when task definitions are heterogeneous and lightweight baselines are competitive. This work presents a protocol-aware empirical assessment across three settings: a C-MAPSS degradation-risk proxy, normal-only training for anomalous-sound detection on MIMII, and BDG2 forecasting-residual diagnostics with synthetic target perturbations. We assess classical one-class methods, compact neural autoencoders, residual forecasters, MOMENT-small, Chronos-T5, and TimesFM 2.5 in terms of anomaly-ranking performance, risk-horizon sensitivity, residual forecasting and perturbation sensitivity, and local implementation cost. Across 100 C-MAPSS engines evaluated out of fold, TCN-AE reaches fold-weighted AUROC/AUPRC 0.9570/0.8960, compared with 0.7310/0.3080 for MOMENT reconstruction; paired engine-cluster bootstrap confidence intervals exclude zero for both differences. Across five matched MIMII pump evaluations, OCSVM also exceeds MOMENT reconstruction in AUROC and AUPRC. On a fixed 12-meter BDG2 panel, TimesFM 2.5 has the lowest aligned forecast error and the highest synthetic AUROC point estimate, although synthetic AUPRC is similar across TSFM and fitted residual models. Same-device measurements show that MOMENT incurs higher latency, peak allocated VRAM, and serialized state-dictionary size than TCN-AE. Under the evaluated frozen and zero-shot settings, TSFMs are task-dependent deployment options rather than default replacements for fitted lightweight models.

District heating energy hubs require reliable heat load forecasts for efficient operational scheduling. Forecasting models trained on historical data may require retraining as networks evolve. Zero-shot time-series foundation models and in-context forecasting therefore offer a promising alternative: they can adapt at inference time from recent observations rather than by repeated retraining. This study systematically evaluates TabPFN-TS and Chronos-2 for probabilistic heat load forecasting in two German district heating networks and compares them with trained baselines. We assess whether TabPFN-TS, whose underlying model is pretrained entirely on synthetic tabular rather than time-series data, can capture complex district heating dynamics. We analyze covariate choice, context length, temporal resolution, and forecast horizon on selected operating weeks, evaluate the selected configuration over the full year, and assess cross-network transfer. The principal benchmark assumes perfect weather forecasts; a separate sensitivity analysis uses retrospective weather predictions. Hourly 24-hour forecasting with a 12-week rolling context and ambient temperature provides a parsimonious configuration; longer context windows do not improve accuracy. Both TSFMs outperform all trained baselines in deterministic accuracy in the full-year benchmarks. Chronos-2 achieves the best deterministic scores, with TabPFN-TS remaining close: their CVRMSE values on the main data set are 12.48% and 13.07%, respectively. Chronos-2 also achieves lower continuous ranked probability scores in both networks, with TabPFN-TS remaining close. a TSFM-based Multi-Resolution Residual-Correction Forecaster combines an hourly base forecast with short-term high-resolution corrections. Relative to direct high-resolution forecasting, it generally reduces errors in total heat demand over 12-hour periods and recorded prediction times.