[2604.04106] InsTraj: Instructing Diffusion Models with Travel Intentions to Generate Real-world Trajectories

Computer Science > Artificial Intelligence arXiv:2604.04106 (cs) [Submitted on 5 Apr 2026] Title:InsTraj: Instructing Diffusion Models with Travel Intentions to Generate Real-world Trajectories Authors:Yuanshao Zhu, Yuxuan Liang, Xiangyu Zhao, Liang Han, Xinwei Fang, Xuetao Wei, James Jianqiao Yu View a PDF of the paper titled InsTraj: Instructing Diffusion Models with Travel Intentions to Generate Real-world Trajectories, by Yuanshao Zhu and 6 other authors View PDF HTML (experimental) Abstract:The generation of realistic and controllable GPS trajectories is a fundamental task for applications in urban planning, mobility simulation, and privacy-preserving data sharing. However, existing methods face a two-fold challenge: they lack the deep semantic understanding to interpret complex user travel intent, and struggle to handle complex constraints while maintaining the realistic diversity inherent in human behavior. To resolve this, we introduce InsTraj, a novel framework that instructs diffusion models to generate high-fidelity trajectories directly from natural language descriptions. Specifically, InsTraj first utilizes a powerful large language model to decipher unstructured travel intentions formed in natural language, thereby creating rich semantic blueprints and bridging the representation gap between intentions and trajectories. Subsequently, we proposed a multimodal trajectory diffusion transformer that can integrate semantic guidance to generate high-fidelity and in...