<ul data-eligibleForWebStory="true"><li>Unified Covariate Adaptation (UniCA) bridges Time Series Foundation Models (TSFMs) with general covariate-aware forecasting to handle diverse covariates like categorical variables and multimodal data.</li><li>UniCA performs covariate homogenization to transform heterogeneous covariates into homogeneous series representations and fuses them using an attention-based fusion mechanism.</li><li>Experiments on various forecasting benchmarks demonstrate the superiority of UniCA in incorporating extra covariate information while preserving the generalization ability of TSFMs.</li><li>Code related to UniCA is available on GitHub for further exploration.</li></ul>

UniCA: Adapting Time Series Foundation Model to General Covariate-Aware Forecasting

Discover more