Xujie Song

Xujie Song
宋绪杰

M.Phil

Tsinghua University

Biography

I hold an M.Phil from the Intelligent Driving Lab (iDLab) at Tsinghua University, working with Prof. Shengbo Li and Prof. Bo Cheng. My research covers neural network, reinforcement learning, autonomous driving and quantum computing. I am dedicated to building more intelligent and safer AI for automated vehicles and robotics, while also developing the next-generation paradigm for neural network training.

Download CV
Interests
  • Neural Network
  • Reinforcement Learning
  • Autonomous Driving
  • Robotics
  • Quantum Computing
Education
  • Tsinghua University, 2021-2024

    M.Phil in Mechanical Engineering

    Minor in Big Data (certificate program)

  • Delft University of Technology, 2017-2021

    Joint Education Program

  • Beijing Jiaotong University, 2017-2021

    B.Eng in Traffic and Transportation

    B.Eng in Computer Science and Technology (dual degree)

Recent News

⚡ $~$ 09 / 2024 $~$ - $~$ 1 paper submitted to Nature Comput. Sci.
⚡ $~$ 09 / 2024 $~$ - $~$ 2 paper submitted to ICLR
🎉 $~$ 09 / 2024 $~$ - $~$ 1 NeurIPS paper is accepted
🎉 $~$ 08 / 2024 $~$ - $~$ 1 IEEE TIV paper is accepted
🎉 $~$ 04 / 2024 $~$ - $~$ Gold award (1$^{\text{st}}$ place) in Wuyue Cup
🎉 $~$ 01 / 2024 $~$ - $~$ Receive RONG Scholarship
🎉 $~$ 05 / 2023 $~$ - $~$ Best Oral Presentation, THU Acad. Forum
🎉 $~$ 04 / 2023 $~$ - $~$ 1 ICML paper is accepted

Publications

Training Multilayer Neural Networks on Ising Machines. Nature Computational Science (NCS), 2024 (under review).

PDF

FlipNet: Fourier Lipschitz Smooth Policy Network for Reinforcement Learning. International Conference on Learning Representations (ICLR), 2025 (under review).

PDF Video Project page

Diffusion Actor-Critic with Entropy Regulator. Annual Conference on Neural Information Processing Systems (NeurIPS), 2024.

PDF

ODE-based Smoothing Neural Network for Reinforcement Learning Tasks. International Conference on Learning Representations (ICLR), 2025 (under review).

PDF

Smooth Filtering Neural Network for Reinforcement Learning. IEEE Transactions on Intelligent Vehicles (TIV), 2024.

PDF Video

A Smooth Reinforcement Learning Method for Trajectory Tracking and Collision Avoidance of Wheeled Vehicle. IEEE Transactions on Intelligent Transportation Systems (TITS), 2024 (under review).

A Method for Training Feedforward Neural Network on Ising Machine. Patent, No. 2023113797497, 2023 (under review).

Smooth Reinforcement Learning Based Trajectory Tracking for Articulated Vehicles. Journal of Harbin Institute of Technology, 2023.

LipsNet: A Smooth and Robust Neural Network with Adaptive Lipschitz Constant for High Accuracy Optimal Control. International Conference on Machine Learning (ICML), 2023.

PDF Code Poster Video

Offline Simulation System for the General Optimal Control Problem Solver (V2.0). Software Copyright, No. 2023SR0225863, 2023.

Code Docs

LiDAR Data Enhancement via Pseudo-LiDAR Point Cloud Correction. Journal of image and Graphics (JIG), 2021.

PDF Code

A Method and Device for 3D Point Cloud Densification Based on Stereo RGB Images. Patent, No. CN111612728B, 2020.

Competition Awards

ACM - ICPC / CCPC
4 Silver Medals, 3 Bronze Medals
ACM - ICPC / CCPC
Wuyue Cup
Gold Award (1st place)
Wuyue Cup
MCM / ICM
Honorable Mention
MCM / ICM
Lanqiao Cup
First Prize
Lanqiao Cup

Honors & Scholarships

2020 Zhixing Scholarship (¥20000, 10 students / year)
2019 Zhixing Minor Scholarship (¥10000, 10 students / year)
2020 National Scholarship (¥8000, Top 1%)
2019 National Scholarship (¥8000, Top 1%)
2018 National Scholarship (¥8000, Top 1%)
2021 Outstanding Graduate, Beijing (Top 5%)

Contact

  • xjsong99@gmail.com
  • Tsinghua University, Beijing, CN 100084