Fangqiang Ding

Postdoctoral Associate @ Massachusetts Institute of Technology

prof_pic2.png

about me

I am a Postdoctoral Associate at MIT, advised by Dr. Hermano Igo Krebs, director of The 77 Lab. Before MIT, I worked with Dr. Or Litany at Technion as a Research Fellow. I was honored to be awarded a 2025 RSS Pioneer for my work on robust spatial perception with 4D radar for mobile autonomy. I received my PhD degree in Robotics and Autonomous Systems from the School of Informatics, University of Edinburgh, supervised by Dr. Chris Xiaoxuan Lu, and my B.Eng degree from Tongji University.

My research centers on reliable and affordable Physical AI, enabling AI-integrated physical systems (e.g., autonomous vehicles, robots, and IoT) to operate responsibly around humans and deliver societal benefits at scale in the physical world. My current work advances this goal along three key axes: (i) condition-adaptive: maintaining robust performance across illumination, weather and environmental changes, (ii) privacy-aware: protecting user identity and sensitive content in privacy-critical applications, (iii) cost-effective: reducing reliance on expensive sensor/compute and manual data collection/labelling for model training.

news

Oct 01, 2025 📖 Started to work as a Postdoctoral Associate at MIT. Look for more collabrations.
May 13, 2025 🎓 Successfully pass my PhD thesis viva. Many thanks to the committee and collaborators.
Apr 21, 2025 🤖 Selected as an RSS Pioneers 2025 (competitive early-career recognition from the robotics community). See you in Los Angeles, USA.
Feb 24, 2025 🎉 One paper accepted to ACM SenSys’25. See you in Irvine, USA.
Jan 27, 2025 📖 Accept to serve as Associate Editor for IROS-2025. Look forward to contribute.
Sep 26, 2024 🎉 One paper accepted to NeurIPS-2024. See you in Vancouver, Canada.

selected publications

  1. Sensys’25
    thermohands.png
    ThermoHands: A Benchmark for 3D Hand Pose Estimation from Egocentric Thermal Image
    Fangqiang Ding, Yunzhou Zhu, Xiangyu Wen, and 2 more authors
    In ACM Conference on Embedded Networked Sensor Systems, 2025
  2. NeurIPS’24
    radarocc.png
    RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar
    Fangqiang Ding, Xiangyu Wen, Yunzhou Zhu, and 2 more authors
    In Advances in Neural Information Processing Systems, 2024
  3. ECCV’24
    milliflow.png
    milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing
    Fangqiang Ding, Zhen Luo, Peijun Zhao, and 1 more author
    In European Conference on Computer Vision, 2024
  4. ICRA’24
    ratrack.png
    RaTrack: Moving Object Detection and Tracking with 4D Radar Point Cloud
    Zhijun Pan, Fangqiang Ding, Hantao Zhong, and 1 more author
    In IEEE International Conference on Robotics and Automation, 2024
  5. CVPR’23
    cmflow.png
    Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision
    Fangqiang Ding, Andras Palffy, Dariu M. Gavrila, and 1 more author
    In IEEE Conference on Computer Vision and Pattern Recognition, 2023
    Selected as Highlight (top 10%)
  6. RA-L/IROS
    raflow.png
    Self-Supervised Scene Flow Estimation with 4D Automotive Radar
    Fangqiang Ding, Zhijun Pan, Yimin Deng, and 2 more authors
    IEEE Robotics Autom. Lett. / IEEE International Conference on Intelligent Robots and Systems, 2022