TrajDLM: Topology-Aware Block Diffusion Language Model for Trajectory Generation

Abstract

Generating high-fidelity synthetic GPS trajectories is increasingly important for applications in transportation, urban planning, and what-if scenario simulation, especially as privacy concerns limit access to real-world mobility data. Existing trajectory generation models face a trade-off between efficiency and faithfulness to road network topology: continuous-space methods enable fast generation but ignore the road network, while topology-aware approaches rely on search-based autoregressive decoding that limits generation speed. We propose TrajDLM, a topology-aware trajectory generation framework based on block diffusion language models that bridges this gap. TrajDLM models trajectories as sequences of discrete road segments, combining a block diffusion backbone for efficient denoising, topology-aware embeddings from a road network encoder, and topology-constrained sampling to ensure coherent and realistic trajectories. Across three city-scale datasets, TrajDLM achieves strong performance on fine-grained local similarity metrics while being up to $2.8\times$ faster than prior work, and demonstrates strong zero-shot transfer across domains, including unseen transportation modes. These results highlight the effectiveness of block-wise discrete diffusion as a scalable approach to accurate and efficient trajectory generation.

BibTeX Citation

@misc{wongso2026trajdlmtopologyawareblockdiffusion,
  title         = {TrajDLM: Topology-Aware Block Diffusion Language Model for Trajectory Generation},
  author        = {Wilson Wongso and Lihuan Li and Arian Prabowo and Xiachong Lin and Baiyu Chen and Hao Xue and Flora D. Salim},
  year          = {2026},
  eprint        = {2605.10020},
  archiveprefix = {arXiv},
  primaryclass  = {cs.LG},
  url           = {https://arxiv.org/abs/2605.10020}
}

Recommended citation: Wongso, W., Li, L., Prabowo, A., Lin, X., Chen, B., Xue, H., & Salim, F. D. (2026). TrajDLM: Topology-Aware Block Diffusion Language Model for Trajectory Generation. arXiv preprint arXiv:2605.10020..
Download Paper