TrajGenAgent is a hierarchical LLM-agent framework that generates human mobility trajectories via in-context activity chain synthesis followed by deterministic visit grounding, evaluated with anomaly-detection detectors for behavioral and semantic plausibility.
Difftraj: Generating gps trajectory with diffusion probabilistic model
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
CityTrajBench standardizes data processing and evaluation for trajectory generators, showing that models like DiffTraj, DiffRNTraj, and TrajFlow each excel on different metrics while a Markov baseline remains competitive on coarse statistics.
A POI-zone and Pareto-calibrated framework infers trip purposes from GPS data and cuts distributional JSD from survey benchmarks by 23-48% on 81 million Los Angeles staypoints.
Generative models for trajectory data do not inherently preserve privacy, as membership inference attacks can identify training data points in representative models.
citing papers explorer
-
TrajGenAgent: A Hierarchical LLM Agent for Human Mobility Trajectory Generation
TrajGenAgent is a hierarchical LLM-agent framework that generates human mobility trajectories via in-context activity chain synthesis followed by deterministic visit grounding, evaluated with anomaly-detection detectors for behavioral and semantic plausibility.
-
CityTrajBench: A Unified Benchmark for City-Scale Vehicle Trajectory Generation
CityTrajBench standardizes data processing and evaluation for trajectory generators, showing that models like DiffTraj, DiffRNTraj, and TrajFlow each excel on different metrics while a Markov baseline remains competitive on coarse statistics.
-
Uncertainty-Aware Trip Purpose Inference from GPS Trajectories via POI Semantic Zones and Pareto Calibration
A POI-zone and Pareto-calibrated framework infers trip purposes from GPS data and cuts distributional JSD from survey benchmarks by 23-48% on 81 million Los Angeles staypoints.
-
Privacy Evaluation of Generative Models for Trajectory Generation
Generative models for trajectory data do not inherently preserve privacy, as membership inference attacks can identify training data points in representative models.