GS-FUSE: Granger-Supervised Gated Fusion and Multi-Granularity Alignment for Event-Driven Financial Forecasting

ArXi:2605.28520v1 Announce Type: new Accurately forecasting the impact of salient financial events on markets is critical for investors and policymakers. However, existing multimodal time-series models typically fuse text and prices symmetrically, without an explicit way to decide when event text is truly predictive, and thus struggle to exploit the directional event-to-price structure and the heterogeneous roles of textual and price signals.