ChronoSteer: Bridging Large Language Model and Time Series Foundation Model via Synthetic Cross-Modal Alignment Dataset
ChronoSteer is a decoupled agentic framework that learns cross-modal alignment from synthetic paired supervision that achieves a 25.8% improvement in zero-shot prediction accuracy over its unimodal backbone, and outperforms prior state-of-the-art unimodal and multimodal ...
Chengsen Wang, Qi Qi, Zhong-Wen Rao et al.
· 0 citations