Honglin He

honglin.jpg

I am a first-year PhD student at the Department of Computer Science, University of California, Los Angeles, advised by Bolei Zhou in the Vision and Autonomy Intelligence Lab (VAIL).

I obtained my Master (2021.09 - 2024.06) at the Department of Automation, Tsinghua University, advised by Professor Yi Zhang and Shuo Feng. Before that, I received my B.Eng (2017.09 - 2021.06) at the Department of Automation, Xiamen University.

My research focuses on Embodied AI, Urban Simulation, and Robot Navigation, with emphasis on building scalable simulation platforms and learning-based navigation policies for autonomous micromobility.

News

Jun 12, 2026

Selected Publications

  1. flowpilot.gif
    FlowPilot
    From Imitation to Alignment: Human-Preference Flow Policies for Long-Horizon Sidewalk Navigation
    Honglin He, Zhizheng Liu, Yukai Ma, and Bolei Zhou
    arXiv preprint, 2026
    Arxiv 2026
  2. mimic.png
    MIMIC
    Learning Sidewalk Autopilot from Multi-Scale Imitation with Corrective Behavior Expansion
    Honglin He, Yukai Ma, Brad Squicciarini, Wayne Wu, and Bolei Zhou
    In IEEE International Conference on Robotics and Automation, 2026
    ICRA 2026
  3. s2e.png
    S2E
    From seeing to experiencing: Scaling navigation foundation models with reinforcement learning
    Honglin He*, Yukai Ma*, Brad Squicciarini, Wayne Wu, and Bolei Zhou
    In International Conference on Learning Representations, 2026
    ICLR 2026
  4. urbanverse.png
    UrbanVerse
    UrbanVerse: Scaling Urban Simulation by Watching City-Tour Videos
    Mingxuan Liu*Honglin He*, Elisa Ricci, Wayne Wu, and Bolei Zhou
    In International Conference on Learning Representations, 2026
    ICLR 2026
  5. urbanx.jpeg
    UrbanSim
    Towards Autonomous Micromobility through Scalable Urban Simulation
    Wayne Wu*Honglin He*, Todd Zhang, Jack He, Ran Gong, Quanyi Li, and Bolei Zhou
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (Highlight), 2025
    CVPR 2025 Highlight
  6. metaurban_short.gif
    MetaUrban
    MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility
    Wayne Wu*Honglin He*, Jack He, Yiran Wang, Chenda Duan, Zhizheng Liu, Quanyi Li, and Bolei Zhou
    International Conference on Learning Representations (Spotlight), 2025
    ICLR 2025 Spotlight
  7. ffhq-geo-high.gif
    OP3D
    Orthoplanes: A novel representation for better 3d-awareness of gans
    Honglin He*, Zhuoqian Yang*, Shikai Li, Bo Dai, and Wayne Wu
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
    ICCV 2023
  8. dna_rendering.gif
    DNA-Rendering
    DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering
    Wei Cheng, Ruixiang Chen, Wanqi Yin, Siming Fan, Keyu Chen, Honglin He, Huiwen Luo, Zhongang Cai, Jingbo Wang, Yang Gao, and 1 more author
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
    ICCV 2023