Tag
LE4Mob is an inductive, distance-aware, and general-purpose location embedding framework for enhancing human mobility modeling in tasks such as next location prediction and commuter flow generation.
This paper introduces geographic domain shift to quantify and analyze the transferability of human mobility flow generation models across regions, revealing spatial heterogeneity and providing a framework for improving GeoAI model development.
The paper proposes MR-Traj, a multi-resolution diffusion framework for synthetic trajectory generation in urban systems, which captures complex spatial-temporal dependencies at multiple resolutions and improves performance in fine-grained mobility modeling for downstream tasks.
Introduces MobiDiff, an end-to-end discrete diffusion framework for generating human mobility data by denoising multi-channel semantic skeletons, achieving faster inference and competitive fidelity on real-world datasets.
This paper introduces a validation framework to evaluate whether LLM-based urban simulators reproduce empirical human mobility patterns. Using data from Paris and Shanghai, the authors find a substantial gap between plausible narratives and realistic mobility constraints, and provide open infrastructure for reproducible evaluation.
TrajGenAgent proposes a hierarchical LLM agent framework that decouples macro-level activity planning from micro-level spatiotemporal instantiation for realistic human mobility trajectory generation without fine-tuning. It also introduces an anomaly-detection-based evaluation for behavioral fidelity.