Xiang Li

Tsinghua University Undergraduate Student, Department of Computer Science and Technology, Tsinghua University

I am currently an undergraduate student of Dept. of Computer Sci. & Tech., THU, and an intern of AIR, THU.
My research interests include 3D Scene Understanding, Autonomous Driving and Embodied AI.


Education
  • Tsinghua University

    Tsinghua University

    Undergraduate Student of Dept. of Computer Sci. & Tech. Sep. 2021 - Now

Honors & Awards
  • Excellent Academic Scholarship 2022 / 2023 / 2024
  • Excellent Art Scholarship 2022 / 2023
  • Freshman Scholarship 2021
Experience
  • Institute for AI Industry Research, Tsinghua University

    Institute for AI Industry Research, Tsinghua University

    Intern Sep. 2023 - Now

  • HKU Musketeers Foundation Institute of Data Science

    HKU Musketeers Foundation Institute of Data Science

    Student Research Assistant Jul. 2024 - Sept. 2024

News
2025
One paper on 3D Occupancy Prediction and 4D Occupancy Forecasting is accepted by ICLR 2025.
Jan 22
2024
One paper on 3D Occupancy Prediction is accepted by ICRA 2024.
Jan 29
Selected Publications (view all )
Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving
Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving

Xiang Li, Pengfei Li, Yupeng Zheng, Wei Sun, Yan Wang, Yilun Chen

International Conference on Learning Representations (ICLR) 2025

Our semi-supervised 3D occupancy world model, featuring 2D rendering supervision and an end-to-end architecture, can forecast future occupancy straightly from image inputs while taking advantage of 2D labels.

Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving
Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving

Xiang Li, Pengfei Li, Yupeng Zheng, Wei Sun, Yan Wang, Yilun Chen

International Conference on Learning Representations (ICLR) 2025

MonoOcc: Digging into Monocular Semantic Occupancy Prediction
MonoOcc: Digging into Monocular Semantic Occupancy Prediction

Yupeng Zheng*, Xiang Li*, Pengfei Li, Yuhang Zheng, Bu Jin, Chengliang Zhong, Xiaoxiao Long, Hao Zhao, Qichao Zhang(* equal contribution)

International Conference on Robotics and Automation (ICRA) 2024

By proposing a distillation module to transfer temporal information and richer knowledge to the monocular branch from a privileged branch, we increase the performance of the framework especially on small and long-tailed objects, while striking a balance between performance and efficiency.

MonoOcc: Digging into Monocular Semantic Occupancy Prediction
MonoOcc: Digging into Monocular Semantic Occupancy Prediction

Yupeng Zheng*, Xiang Li*, Pengfei Li, Yuhang Zheng, Bu Jin, Chengliang Zhong, Xiaoxiao Long, Hao Zhao, Qichao Zhang(* equal contribution)

International Conference on Robotics and Automation (ICRA) 2024

All publications