SceneSelect: Selective Learning for Trajectory Scene Classification and Expert Scheduling

ArXi:2604.24514v1 Announce Type: new Accurate trajectory prediction is fundamentally challenging due to high scene heterogeneity - the severe variance in motion velocity, spatial density, and interaction patterns across different real-world environments. However, most existing approaches typically train a single unified model, expecting a fixed-capacity architecture to generalize universally across all possible scenarios.