Bolei Zhou

Assistant Professor
Computer Science Department, University of California, Los Angeles
Office: 295D, Engineering VI, UCLA.
PTE request or Prospective Student please read this

My research is at the intersection of computer vision and robot learning, with a focus on developing efficient, interpretable, and generalizable AI agents (both embodied and virtual) that aligns with humans. I am also interested in understanding various human-centric properties of current AI models beyond their accuracy, such as explainability, interpretability, steerability, generalization, and safety. Some of the earlier works I co-authored are Class Activation Mapping (CAM), Places, ADE20K, Network Dissection.

See MetaDriverse for our recent work on robot learning and embodied AI.
See GenForce for our recent work on generative modeling and GenAI.

News

Jan 23, 2025 Thank ONR for supporting our research via ONR Young Investigator Award, with news of UCLA, Samueli Engineering School, CS department.
Jul 31, 2024 Check out the newest urban environment simulator MetaUrban for embodied AI research in micromobility.
Jul 31, 2024 My talk record at CVPR’24 Workshop on Autonomous Driving summarizes our effort of building the open-source simulation platform MetaDriverse for AI research and mobility. Slide is available.
Jun 12, 2024 CVPR’2024: give invited talks at Workshop on Autonomous Driving (WAD) on 06/17 AM and Workshop on Robot Visual Perception in Human Crowded Environments on 06/18 PM, and co-organize Workshop on Populating Empty Cities on 06/17 PM.
Feb 13, 2024 Thank NSF for supporting our research via NSF CAREER Award.
Sep 12, 2023 Thank Intel for supporting our research via Intel’s 2023 Rising Star Faculty Award.
Apr 26, 2023 Invited talks at workshops on coPerception: collaborative perception and learning at ICRA’23, end-to-end autonomous driving at CVPR’23, and secure and safe autonomous driving at CVPR’23, and BIRS workshop on 3D generative models.
Mar 24, 2023 Grateful to receive NSF award for supporting our research of developing our MetaDrive driving simulator into MetaDriverse, an open-source infrastructure for AI research on autonomous driving.
Jan 9, 2023 I summarize our effort of going from Network Dissection to Policy Dissection in the talk Discovering Interpretable Concepts in Deep Representations at IPAM Workshop on Explainable AI for the Sciences: Towards Novel Insights.

Selected Publications

  1. CVPR
    Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation
    Ziyang Xie, Zhizheng Liu, Zhenghao Peng, Wayne Wu, and Bolei Zhou
    IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR) , 2025
  2. CVPR
    Embodied Scene Understanding for Vision Language Models via MetaVQA
    Weizhen Wang, Chenda Duan, Zhenghao Peng, Yuxin Liu, and Bolei Zhou
    IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR) , 2025
  3. ICRA
    Data-Efficient Learning from Human Interventions for Mobile Robots
    Zhenghao Peng, Zhizheng Liu, and Bolei Zhou
    IEEE International Conference on Robotics and Automation (ICRA) , 2025
  4. ICLR 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 (ICLR Spotlight) , 2025
  5. ICLR
    Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labels
    Zhizheng Liu, Joe Lin, Wayne Wu, and Bolei Zhou
    International Conference on Learning Representations (ICLR) , 2025
  6. ICLR
    3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting
    Qihang Zhang, Yinghao Xu, Chaoyang Wang, Hsin-Ying Lee, Gordon Wetzstein, Bolei Zhou, and Ceyuan Yang
    International Conference on Learning Representations (ICLR) , 2025
  7. NeurIPS
    SimGen: Simulator-conditioned Driving Scene Generation
    Yunsong Zhou, Michael Simon, Zhenghao Peng, Sicheng Mo, Hongzi Zhu, Minyi Guo, and Bolei Zhou
    Advances in Neural Information Processing Systems (NeurIPS) , 2024
  8. NeurIPS
    Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance
    Kuan Heng Lin, Sicheng Mo, Ben Klingher, Fangzhou Mu, and Bolei Zhou
    Advances in Neural Information Processing Systems (NeurIPS) , 2024
  9. NeurIPS
    Shared Autonomy with IDA: Interventional Diffusion Assistance
    Brandon J McMahan, Zhenghao Peng, Bolei Zhou, and Jonathan C Kao
    Advances in Neural Information Processing Systems (NeurIPS) , 2024
  10. Nature
    Experiment-free Exoskeleton Assistance via Learning in Simulation
    Shuzhen Luo, Menghan Jiang, Sainan Zhang, Junxi Zhu, Shuangyue Yu, Israel Dominguez Silva, Tian Wang, Elliott Rouse, Bolei Zhou, Hyunwoo Yuk, Xianlian Zhou, and Hao Su
    Nature , 2024
  11. CVPR
    FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition
    Sicheng Mo, Fangzhou Mu, Kuan Heng Lin, Yanli Liu, Bochen Guan, Yin Li, and Bolei Zhou
    IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR) , 2024
  12. CVPR
    Scenewiz3d: Towards text-guided 3d scene composition
    Qihang Zhang, Chaoyang Wang, Aliaksandr Siarohin, Peiye Zhuang, Yinghao Xu, Ceyuan Yang, Dahua Lin, Bolei Zhou, Sergey Tulyakov, and Hsin-Ying Lee
    IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR) , 2024
  13. RAL
    Street-View Image Generation from a Bird’s-Eye View Layout
    Alexander Swerdlow, Runsheng Xu, and Bolei Zhou
    IEEE Robotics and Automation Letters (RAL) , 2024