aiqbench analysis
This paper introduces MR-Traj, a multi-resolution diffusion framework designed to generate synthetic human mobility data while preserving privacy by reducing linkage risks. By explicitly modeling trajectories as coarse milestones combined with fine-grained segments, the method captures complex spatiotemporal dependencies essential for urban applications like traffic management and epidemic control. The approach outperforms existing techniques in generating diverse patterns that satisfy both global distribution constraints and high-resolution utility requirements without relying on large-scale public datasets.
Coarse-to-Fine Multi-Resolution Diffusion Models for Trajectory Generation in Urban Systems
arXiv:2608.14570v1 Announce Type: new Abstract: Understanding human mobility is critical for a wide range of urban applications, including traffic management, epidemic control, and urban planning. However, due to privacy concerns, the availability of large-scale public trajectory data remains limited, posing challenges for downstream mobility analysis. Existing methods for synthetic trajectory generation primarily focus on matching global distribution similarity, while often overlooking mobility patterns across different spatial and temporal resolutions that are essential for practical utility. To address these challenges, we propose a novel multi-resolution diffusion framework, MR-Traj, for large-scale trajectory generation. MR-Traj explicitly models trajectories as compositions of coarse-grained milestones and fine-grained segments, enabling the capture of complex spatial-temporal dependencies at multiple resolutions. Experimental results demonstrate that MR-Traj achieves comparable performance to state-of-the-art methods in terms of global distribution similarity, while consistently outperforming them in modeling fine-resolution mobility patterns and supporting downstream urban mobility tasks. In addition, by introducing stochasticity at multiple resolution levels, MR-Traj generates more diverse trajectories, which empirically reduces trajectory linkage risk under a seed-guided data release setting. Our code is available at https://github.com/Ray0202/MR-Traj.
Abstract:Understanding human mobility is critical for a wide range of urban applications, including traffic management, epidemic control, and urban planning. However, due to privacy concerns, the availability of large-scale public trajectory data remains limited, posing challenges for downstream mobility analysis. Existing methods for synthetic trajectory generation primarily focus on matching global distribution similarity, while often overlooking mobility patterns across different spatial and temporal resolutions that are essential for practical utility. To address these challenges, we propose a novel multi-resolution diffusion framework, MR-Traj, for large-scale trajectory generation. MR-Traj explicitly models trajectories as compositions of coarse-grained milestones and fine-grained segments, enabling the capture of complex spatial-temporal dependencies at multiple resolutions. Experimental results demonstrate that MR-Traj achieves comparable performance to state-of-the-art methods in terms of global distribution similarity, while consistently outperforming them in modeling fine-resolution mobility patterns and supporting downstream urban mobility tasks. In addition, by introducing stochasticity at multiple resolution levels, MR-Traj generates more diverse trajectories, which empirically reduces trajectory linkage risk under a seed-guided data release setting. Our code is available at this https URL.
12 pages, 4 figures. Accepted to KDD 2026
Machine Learning (cs.LG)
arXiv:2608.14570 [cs.LG]
(or arXiv:2608.14570v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.14570 Focus to learn more arXiv-issued DOI via DataCite
https://doi.org/10.1145/3770855.3818889 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 284 words
Related coverage
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · Sep 25, 2026
Research Note: Filtering Subversion-Relevant Information From Pretraining Data Is Feasible
LessWrong · Oct 5, 2026
Sig-DEG for Distillation: Making Diffusion Models Faster and Lighter
arXiv · Oct 15, 2026
Plan-to-Synthesis: Cross-City Human Mobility Generation via Semantic Latent Flow Matching
arXiv · Sep 30, 2026