arXiv Machine Learning
Latent Inference-Time Guidance of Time Series Foundation Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 5
TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning
arXiv:2606. 05878v1 Announce Type: new Abstract: Foundation models mark a profound paradigm shift in time series modeling, with task-specific models being superseded by general-purpose zero-shot models.
arXiv AI
Jun 2
VLBM: Variational Latent Basis Modeling for OOD Robust Multivariate Time Series Forecasting
arXiv:2606. 02138v1 Announce Type: cross Abstract: Out of distribution (OOD) events in multivariate time series forecasting are rare but often dominate real world risk, making average case forecasting insufficient for reliable deployment.
arXiv Machine Learning
Aug 17
Model-agnostic Retrieval-Augmented Extended Forecasting for time series
arXiv:2608. 14054v1 Announce Type: new Abstract: Time series forecasting with pretrained foundation models has demonstrated strong zero-shot capabilities.
arXiv Machine Learning
Aug 27
NVExplain: Explaining Time Series Forecasting with Latent Trajectory Analysis and Structure-Preserving Surrogates
NVExplain is a model‑agnostic framework that explains time‑series forecasting by attributing each forecast horizon to temporally relevant historical lags. It models forecasting as a latent trajectory, introduces semantic flow to track information evolution, and aggregates this into a lag‑horizon attribution matrix. The method also generates structure‑preserving perturbations and fits sparse local surrogates to produce human‑readable, temporally coherent explanations, and demonstrates competitive faithfulness and stability across benchmark datasets.
arXiv Machine Learning
2d ago
Aurora-X: Built for Extreme Time Series Forecasting
Aurora‑X is a billion‑parameter time‑series foundation model designed for extreme forecasting tasks. It employs a progressive curriculum that starts with channel‑independent pretraining, then adds cross‑variable dependencies, variable context and horizon lengths, and optional future covariates during mid‑training. A variable‑resolution post‑training stage allows adjustable temporal spans per token at inference, while a pattern‑guided mixture‑of‑experts expands capacity through sparse activation and expert specialization. An implicit quantile network head predicts arbitrary quantiles, enhancing probabilistic forecasting flexibility. Experiments on GIFT‑Eval, TIME, FEV‑Bench, TFB, and DAG‑Bench show state‑of‑the‑art performance against both pretrained TSFMs and task‑specific supervised models.
arXiv Machine Learning
Sep 23
Interweaving Marginals into Multivariate Sample Paths: Training-Free Dependence Construction for Probabilistic Time Series Foundation Models
arXiv:2609.25980v1 Announce Type: new Abstract: Probabilistic time series foundation models (TSFMs) provide coordinate-wise predictive distributions, but these marginals do not determine a joint dist...