Learning to Factorize and Adapt: A Versatile Approach Toward Universal Spatio-Temporal Foundation Models

TL;DR

FactoST-v2 introduces a factorized spatio-temporal foundation model that decouples temporal learning from spatial adaptation, achieving state-of-the-art accuracy efficiently across diverse domains in zero-shot and few-shot settings.

Contribution

The paper presents a novel factorized framework for spatio-temporal modeling that enables full weight transfer and arbitrary-length generalization, improving efficiency and versatility.

Findings

Achieves state-of-the-art accuracy across multiple domains.

Outperforms existing models in zero-shot and few-shot scenarios.

Maintains linear efficiency while scaling to diverse tasks.

Abstract

Spatio-Temporal (ST) Foundation Models (STFMs) promise cross-dataset generalization, yet joint ST pretraining is computationally expensive and grapples with the heterogeneity of domain-specific spatial patterns. Substantially extending our preliminary conference version, we present FactoST-v2, an enhanced factorized framework redesigned for full weight transfer and arbitrary-length generalization. FactoST-v2 decouples universal temporal learning from domain-specific spatial adaptation. The first stage pretrains a minimalist encoder-only backbone using randomized sequence masking to capture invariant temporal dynamics, enabling probabilistic quantile prediction across variable horizons. The second stage employs a streamlined adapter to rapidly inject spatial awareness via meta adaptive learning and prompting. Comprehensive evaluations across diverse domains demonstrate that FactoST-v2 achieves state-of-the-art accuracy with linear efficiency - significantly outperforming existing foundation models in zero-shot and few-shot scenarios while rivaling domain-specific expert baselines. This factorized paradigm offers a practical, scalable path toward truly universal STFMs. Code is available at https://github.com/CityMind-Lab/FactoST.