Logo 2
Vision and Autonomy Intelligence Lab
UrbanVerse: Scaling Urban Simulation by Watching City-Tour Videos
From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning
Joint Optimization for 4D Human-Scene Reconstruction in the Wild
SceneStreamer: Continuous Scenario Generation as Next Token Group Prediction
Towards Autonomous Micromobility through Scalable Urban Simulation
Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation
Dreamland: Controllable World Creation with Simulator and Generative Models
Predictive Preference Learning from Human Interventions

News

May 14, 2026 Zhihao Zhao won the Qualcomm Innovation Fellowship 2026.
Apr 21, 2026 Ziyang Leng won the Outstanding Graduating MS Student of UCLA CS department.
Mar 11, 2026 MIMIC was accepted to ICRA 2026.
Mar 11, 2026 AURA, GroupDiff, and Vista4D (Highlight) were accepted to CVPR 2026.
Jan 26, 2026 JOSH, S2E, UrbanVerse and SceneStreamer were accepted to ICLR 2026.
Dec 17, 2025 Joe Lin won the 2025–2026 CRA Outstanding Undergraduate Researcher Award Honorable Mention.
Dec 16, 2025 Our lab is honored to receive an NVIDIA Academic Grant to Advance Physical AI for Micromobility. Excited to build our urban simulation with RTX PRO 6000, Jetson Orin, and Ominiverse.
Oct 23, 2025 Wayne Wu won the 2025 Chancellor’s Award for Postdoctoral Research at UCLA.
Sep 18, 2025 PPL (Spotlight), Adv-BMT, and AutoVLA were accepted to NeurIPS 2025.
Aug 20, 2025 Honglin He won the Amazon Trainium Fellowship.
Aug 20, 2025 Sicheng Mo won the Amazon AI Fellowship.
Jul 05, 2025 We released code for Urban-Sim, the newest simulator for embodied AI research in urban micromobility.
Jun 25, 2025 X-Fusion and ST-Occ were accepted to ICCV 2025.
Jun 11, 2025 We co-organized Workshop on Populating Empty Cities and Workshop on Real-to-Sim: Bridging the Gap between Neural Rendering and Robot Learning at CVPR 2025.
Jun 11, 2025 Prof. Zhou gave talks at Synthetic Data for Computer Vision Workshop, AVA: Accessbility, Vision, and Autonomy Workshop, 4th Workshop on Uncertainty Quantification for Computer Vision at CVPR 2025.
May 01, 2025 AIM was accepted to ICML 2025.
Apr 05, 2025 Zhenghao Peng won the Dissertation Year Award (DYA) at UCLA.
Mar 25, 2025 Jordan Lin named 2024–2025 CRA Outstanding Undergraduate Researcher Award Finalist.
Feb 26, 2025 Urban-Sim (Highlight), Vid2Sim, and MetaVQA were accepted to CVPR 2025.
Jan 23, 2025 Prof. Zhou won the 2025 ONR Young Investigator Award.
Jun 14, 2024 Zhenghao Peng won the Amazon Fellowship.
Jun 12, 2024 We co-organized Workshop on Populating Empty Cities at CVPR 2024.
Jun 12, 2024 Prof. Zhou gave talks at Workshop on Autonomous Driving (WAD) and Workshop on Robot Visual Perception in Human Crowded Environment at CVPR 2024.
Feb 13, 2024 Prof. Zhou won the NSF CAREER Award.

Recent Papers

  1. Arxiv
    Image
    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
    PDF Website
  2. Arxiv
    Image
    Monocular 3D Occupancy Perception for Robots on Sidewalks via Hybrid 2D-3D Learning
    Yukai Ma, Joe Lin, Liu Liu, Honglin He, Lulu Ricketts, Brad Squicciarini, Yong Liu, and Bolei Zhou
    arXiv preprint, 2026
    Website
  3. Arxiv
    Image
    SidewalkBench: Benchmarking Visual Navigation on Urban Sidewalks
    Zhizheng Liu, Honglin He, Vivek Alumootil, Akshat Pandya, Brad Squicciarini, Wayne Wu, and Bolei Zhou
    arXiv preprint, 2026
    PDF Website
  4. ICRA
    Image
    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
    PDF Website
  5. CVPR
    Image
    AURA: Multi-modal Shared Autonomy for Urban Navigation
    Yukai Ma, Honglin He, Selina Song, Wayne Wu, and Bolei Zhou
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026
    PDF Website
  6. CVPR
    Image
    Group Diffusion: Enhancing Image Generation by Unlocking Cross-Sample Collaboration
    Sicheng Mo, Thao Nguyen, Richard Zhang, Nicholas Kolkin, Siddharth Srinivasan Iyer, Eli Shechtman, Krishna Kumar Singh, Yong Jae Lee, Bolei Zhou, and Yuheng Li
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026
    PDF Website
  7. CVPR Highlight
    Image
    Vista4D: Video Reshooting with 4D Point Clouds
    Kuan Heng Lin, Zhizheng Liu, Pablo Salamanca, Yash Kant, Ryan Burgert, Koichi Namekata, Yiwei Zhao, Bolei Zhou, Micah Goldblum, Paul Debevec, and Ning Yu
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026
    PDF Website
  8. CVPR
    Image
    AnimaMimic: Imitating 3D Animation from Video Priors
    Tianyi Xie, Yunuo Chen, Yaowei Guo, Yin Yang, Bolei Zhou, Demetri Terzopoulos, Ying Jiang, and Chenfanfu Jiang
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026
    PDF Website
  9. HRI
    Image
    DiSCo: Diffusion Sequence Copilots for Shared Autonomy
    Andy Wang, Xu Yan, Brandon McMahan, Michael Zhou, Yuyang Yuan, Johannes Y. Lee, Ali Shreif, Matthew Li, Zhenghao Peng, Bolei Zhou, Yuchen Cui, and Jonathan C. Kao
    In Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction, 2026
    PDF Website
  10. ICLR
    Image
    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 Representation, 2026
    PDF Website
  11. ICLR
    Image
    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 Representation, 2026
    PDF Website
  12. ICLR
    Image
    Joint Optimization for 4D Human-Scene Reconstruction in the Wild
    Zhizheng Liu, Joe Lin, Wayne Wu, and Bolei Zhou
    In International Conference on Learning Representation, 2026
    PDF Website
  13. ICLR
    Image
    SceneStreamer: Continuous Scenario Generation as Next Token Group Prediction
    Zhenghao Peng, Yuxin Liu, and Bolei Zhou
    In International Conference on Learning Representation, 2026
    PDF Website
  14. Arxiv
    Image
    Dreamland: Controllable World Creation with Simulator and Generative Models
    Sicheng Mo, Ziyang Leng, Leon Liu, Weizhen Wang, Honglin He, Huizhi Zhang, and Bolei Zhou
    arXiv preprint, 2025
    PDF Website
  15. NeurIPS Spotlight
    Image
    Predictive Preference Learning from Human Interventions
    Haoyuan Cai, Zhenghao Peng, and Bolei Zhou
    In Advances in Neural Information Processing Systems, 2025
    PDF Website
  16. NeurIPS
    Image
    Adv-BMT: Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation
    Yuxin Liu, Zhenghao Peng, Xuanhao Cui, and Bolei Zhou
    In Advances in Neural Information Processing Systems, 2025
    PDF Website
  17. NeurIPS
    Image
    AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning
    Zewei Zhou, Tianhui Cai, Seth Z Zhao, Yun Zhang, Zhiyu Huang, Bolei Zhou, and Jiaqi Ma
    In Advances in Neural Information Processing Systems, 2025
    PDF Website
  18. ICCV
    Image
    X-Fusion: Introducing New Modality to Frozen Large Language Models
    Sicheng Mo, Thao Nguyen, Xun Huang, Siddharth Srinivasan Iyer, Yijun Li, Yuchen Liu, Abhishek Tandon, Eli Shechtman, Krishna Kumar Singh, Yong Jae Lee, Bolei Zhou, and Yuheng Li
    In International Conference on Computer Vision, 2025
    PDF Website
  19. ICCV
    Image
    Occupancy Learning with Spatiotemporal Memory
    Ziyang Leng, Jiawei Yang, Wenlong Yi, and Bolei Zhou
    In International Conference on Computer Vision, 2025
    PDF Website
  20. IROS
    Image
    CooPre: Cooperative Pretraining for V2X Cooperative Perception
    Seth Z. Zhao, Hao Xiang, Chenfeng Xu, Xin Xia, Bolei Zhou, and Jiaqi Ma
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025
    PDF Website