JointFM-0.1: A Foundation Model for Multi-Target Joint Distributional Prediction

TL;DR

JointFM is a novel foundation model that directly predicts joint probability distributions of coupled time series, bypassing traditional SDE calibration and enabling zero-shot distributional forecasting.

Contribution

It introduces the first foundation model for distributional predictions of coupled time series, trained on synthetic SDEs without task-specific calibration or fine-tuning.

Findings

Reduces energy loss by 21.1% compared to baselines.

Operates effectively in a zero-shot setting.

Predicts joint distributions directly from synthetic SDEs.

Abstract

Despite the rapid advancements in Artificial Intelligence (AI), Stochastic Differential Equations (SDEs) remain the gold-standard formalism for modeling systems under uncertainty. However, applying SDEs in practice is fraught with challenges: modeling risk is high, calibration is often brittle, and high-fidelity simulations are computationally expensive. This technical report introduces JointFM, a foundation model that inverts this paradigm. Instead of fitting SDEs to data, we sample an infinite stream of synthetic SDEs to train a generic model to predict future joint probability distributions directly. This approach establishes JointFM as the first foundation model for distributional predictions of coupled time series - requiring no task-specific calibration or finetuning. Despite operating in a purely zero-shot setting, JointFM reduces the energy loss by 21.1% relative to the strongest baseline when recovering oracle joint distributions generated by unseen synthetic SDEs.