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

Feb 27, 2026 AURA (Multi-modal Shared Autonomy for Urban Navigation) accepted to CVPR 2026.
Jan 30, 2026 MIMIC (Learning Sidewalk Autopilot from Multi-Scale Imitation) accepted to ICRA 2026.
Jan 22, 2026 Two papers accepted to ICLR 2026: S2E and UrbanVerse.
Aug 20, 2025 I received the Amazon Trainium Fellowship. :tada:

Selected Publications

  1. Arxiv 2026
    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
    PDF Website
  2. ICLR 2026
    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
    PDF Website
  3. ICLR 2026
    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
    PDF Website
  4. CVPR 2025 Highlight
    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
    PDF Website
  5. metaurban_short.gif
    ICLR 2025 Spotlight
    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
    PDF Website
  6. ffhq-geo-high.gif
    ICCV 2023
    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
    PDF Website
  7. dna_rendering.gif
    ICCV 2023
    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
    PDF Website