Publications

2026

  1. Deconstructing Spatial Complexity: Hierarchical Decomposition for LLM Spatial Reasoning
    Yi Wang ,  Haojie Lu ,  Zhaofan Zhang ,  Li Chen ,  and  Sihong Xie
    arXiv preprint arXiv:2605.28144, 2026
    arXiv
  2. Quantile Geometry Regularization for Distributional Reinforcement Learning
    Zhaofan Zhang ,  Minghao Yang ,  Rufeng Chen ,  Sihong Xie ,  and  Hui Xiong
    arXiv preprint arXiv:2605.08182, 2026
    arXiv
  3. Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning
    Rufeng Chen ,  Zhaofan Zhang ,  Zhejian Yang ,  Hechang Chen ,  and  Sihong Xie
    arXiv preprint arXiv:2605.02777, 2026
    arXiv
  4. RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation
    Yi Chang ,  Rufeng Chen ,  Zhaofan Zhang ,  Yan Chen ,  Yu Tian ,  and  Sihong Xie
    arXiv preprint arXiv:2601.10168, 2026
    arXiv

2025

  1. Unifying Modern AI with Robotics: Survey on MDPs with Diffusion and Foundation Models
    Zhaofan Zhang ,  Rufeng Chen ,  Zhejian Yang ,  Sihong Xie ,  Hechang Chen ,  and  Hui Xiong
    TechRxiv preprint, 2025
    HTML
  2. Perturbation-mitigated USV Navigation with Distributionally Robust Reinforcement Learning
    Zhaofan Zhang ,  Minghao Yang ,  Sihong Xie ,  and  Hui Xiong
    arXiv preprint arXiv:2512.00030, 2025
    arXiv

2024

  1. Spatial-Temporal Interplay in Human Mobility: A Hierarchical Reinforcement Learning Approach with Hypergraph Representation
    Zhaofan Zhang ,  Yanan Xiao ,  Lu Jiang ,  Dingqi Yang ,  Minghao Yin ,  and  Pengyang Wang
    In Proceedings of the AAAI Conference on Artificial Intelligence , 2024
    arXiv