Chris Xiaoxuan Lu

Associate Professor @ Department of Computer Science, University College London

I am an Associate Professor in Robotics and AI at the Department of Computer Science, University College London (UCL). My research centers on Scaling Foundation Models for Embodied AI, leveraging recent advancements in AI and machine learning to adapt foundation models for real-world applications. These models offer unparalleled context-awareness in a zero-shot manner, enabling intelligent behavior without task-specific training. My work addresses the significant challenges of deploying these foundation models in diverse and unpredictable environments, focusing on three key areas:

  1. Generalization Across Modalities – Ensuring robust performance of AI models across various sensors used by different agents.

  2. Computational Efficiency – Optimizing foundation models to run effectively on limited hardware resources.

  3. Human-Machine Interaction – Facilitating seamless and intuitive interactions between AI systems, human users, and other machines.

At the core of my research is the mission to enable embodied AI systems to operate reliably in real-world settings. Discover more about my research projects on my research page.

Before coming to UCL, I was a faculty member at the University of Edinburgh and University of Liverpool. I did both my PhD study and post-doctoral in the Department of Computer Science, University of Oxford. Even earlier, I received my M.Eng degree from Nanyang Technological University (NTU).

news

Dec 2, 2024 🔍 We have an EPSRC-DTP PhD studentship on multi-modal visual-language-action model for robotic manipulation. Find more details on the vacancies page.
Sep 26, 2024 🎉 One papers accepted to NeurIPS-2024. Stay tuned for the code and video release. See you in Vancouver, Canada.
Jul 2, 2024 🎉 Two papers accepted to ECCV-2024 and one paper accepted to IROS-2024. Stay tuned for the code and video release. See you at Milano and Abu Dhabi.
Jan 29, 2024 🎉 Three papers accepted to ICRA-2024. Stay tuned for the code and video release. See you at Yokohama in May.

selected publications

  1. NeurIPS’24
    RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar
    Fangqiang Ding, Xiangyu Wen, Yunzhou Zhu, Yiming Li, and Chris Xiaoxuan Lu
    In The Thirty-eighth Conference on Neural Information Processing Systems 2024
    arXiv Video Code Website
  2. ECCV’24
    Self-Adapting Large Visual-Language Models to Edge Devices across Visual Modalities
    Kaiwen Cai, Zhekai Duan, Gaowen Liu, Charles Fleming, and Chris Xiaoxuan Lu
    In The European Conference on Computer Vision 2024
    arXiv Video Code
  3. ICRA’24
    Moving Object Detection and Tracking with 4D Radar Point Cloud
    Zhijun Pan, Fangqiang Ding, Hantao Zhong, and Chris Xiaoxuan Lu
    In IEEE International Conference on Robotics and Automation 2024
    arXiv Video Code
  4. IROS’24
    Click to Grasp: Zero-Shot Precise Manipulation via Visual Diffusion Descriptors
    Nikolaos Tsagkas, Jack Rome, Subramanian Ramamoorthy, Oisin Mac Aodha, and Chris Xiaoxuan Lu
    In IEEE/RSJ International Conference on Intelligent Robots and Systems 2024
    arXiv Website
  5. CVPR’23
    Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision
    Fangqiang Ding, Andras Palffy, Dariu M. Gavrila, and Chris Xiaoxuan Lu
    In IEEE Conference on Computer Vision and Pattern Recognition 2023
    CVPR’23 Highlight
    arXiv Video Code Website
  6. T-RO
    Graph-Based Thermal–Inertial SLAM With Probabilistic Neural Networks
    Muhamad Risqi U. Saputra, Chris Xiaoxuan Lu, Pedro Porto B. Gusmao, Bing Wang, Andrew Markham, and Niki Trigoni
    IEEE Transactions on Robotics 2022
    arXiv Video Code
  7. ICRA’22
    AutoPlace: Robust Place Recognition with Single-chip Automotive Radar
    Kaiwen Cai, Bing Wang, and Chris Xiaoxuan Lu
    In International Conference on Robotics and Automation (ICRA) 2022
    arXiv Video Code Website
  8. MobiSys’20
    See through smoke: robust indoor mapping with low-cost mmWave radar
    Chris Xiaoxuan Lu, Stefano Rosa, Peijun Zhao, Bing Wang, Changhao Chen, John A. Stankovic, Niki Trigoni, and Andrew Markham
    In The 18th Annual International Conference on Mobile Systems, Applications, and Services (MobiSys) 2020
    arXiv HTML Video Code
  9. SenSys’20
    milliEgo: single-chip mmWave radar aided egomotion estimation via deep sensor fusion
    Chris Xiaoxuan Lu, Muhamad Risqi U. Saputra, Peijun Zhao, Yasin Almalioglu, Pedro P. B. Gusmao, Changhao Chen, Ke Sun, Niki Trigoni, and Andrew Markham
    In The 18th ACM Conference on Embedded Networked Sensor Systems (SenSys) 2020
    arXiv HTML Video Code
  10. AAAI’18
    IONet: Learning to Cure the Curse of Drift in Inertial Odometry
    Changhao Chen, Chris Xiaoxuan Lu, Andrew Markham, and Niki Trigoni
    In The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI) 2018
    arXiv HTML Video