In Part 1 of this series, we introduced Chronos-2, a time-series foundation model. We got our hands dirty by walking through a real case study and saw what Chronos-2 can do straight out of the box, with no training.
Part 1: A practitioner's walkthrough of univariate, multivariate, covariate-informed, and cold-start forecasting. The post Five Questions About Chronos-2, the Time Series Foundation Model appeared first on Towards Data Science .
arXiv:2608.24303v1 Announce Type: new Abstract: Transitioning from bespoke time series models towards time series foundation models changes the relationship of model and application from one-to-one t...
arXiv:2606. 27438v1 Announce Type: new Abstract: Since its initial release in 2020, Darts has become a widely used open-source Python library for time series analysis.
arXiv:2510. 00809v3 Announce Type: replace Abstract: While Time Series Foundation Models (TSFMs) excel in zero-shot tasks, their behavior under continual fine tuning is poorly understood.
arXiv:2605. 20119v2 Announce Type: replace Abstract: We show that time series foundation models scale: a single training recipe produces reliable forecast-quality improvements from 4M to 2.
The paper introduces SimpleTimeBench, a diagnostic suite testing basic temporal primitives like monotonic trends, periodic signals, and leading indicator covariates. It finds that prominent multivariate Time Series Foundation Models (Chronos‑2, Moirai, and Toto) often produce suboptimal zero‑shot forecasts for these simple patterns, and that fine‑tuning can improve specific tasks while harming performance on other fundamentals. These failures persist in real‑world sensor forecasting, indicating that current TSFMs may lack the inductive biases needed to capture straightforward relationships, thereby limiting their practical reliability.
arXiv:2606. 07457v1 Announce Type: new Abstract: At commissioning time, Photovoltaic (PV) operators must forecast production before target-site observations are available, limiting the direct use of standard supervised forecasters.
An open, 2. 8-trillion-parameter model shipped with 47 pages of its own recipe.
The paper introduces VINTAGE-TS, a revision‑aware time‑series foundation model that separates observation time from information‑availability time. It predicts both the next period’s first‑published value and the value available after a fixed delay, maintaining a joint distribution to capture their dependence and uncertainty. The authors provide a detailed evaluation protocol, software tools for validity‑interval reconstruction and delayed‑label filtering, and a synthetic demonstration with a 25‑configuration sensitivity suite to illustrate performance variability and the impact of hindsight contamination.
arXiv:2607. 04919v1 Announce Type: new Abstract: Deploying a time series foundation model requires GPU infrastructure, engineering overhead, and carries no guarantee of improvement over XGBoost.
arXiv:2411. 11350v2 Announce Type: replace Abstract: Deep learning models have shown strong performance in load forecasting, but they generally require large amounts of data for model training before being applied to new scenarios, which limits their effectiveness in data-scarce scenarios.
The paper argues that zero‑shot time‑series forecasting should be treated as an evidence‑access claim rather than merely a no‑parameter‑update condition. It introduces a source‑first taxonomy that distinguishes three evidence sources—frozen LLM prior reuse, parametric time‑series pretraining, and retrieval‑augmented external memory—from the architectures that implement them. The authors further outline four audit questions—task interface, forecast object and scoring, prediction‑time context, and resource budget—to make zero‑shot leaderboards transparent and comparable.