TrajPrism: A Multi-Task Benchmark for Language-Grounded Urban Trajectory Understanding

ArXi:2605.10782v1 Announce Type: new Urban mobility is naturally expressed both as trajectories in space and as natural-language descriptions of travel intent, constraints, and preferences. However, prior work rarely evaluates these two modalities together on the same real-world trajectories: trajectory modeling often stays geometry-centric, while language-centric mobility benchmarks frequently target route planning and tool use rather than fine-grained, verifiable alignment between text and the underlying route. We