Quanyi Li

I am an MRes student at IPAB, University of Edinburgh, advised by Prof. Ram Ramamoorthy. Previously, I was a research assistant at Multimedia Lab (MMLab), The Chinese University of Hong Kong, working with Prof. Bolei Zhou. I received my bachelor degree at Bejing University of Posts and Telecommunications under the supervision of Prof. Haipeng Yao in July 2020.

When I was a senior student, I did an internship at SenseTime and worked with Dr. Chunxiao Liu. Now I am working with Dr. Jiangmiao Pang at Shanghai AI Lab.


Research

I am interested in Embodied AI with its generalizability, safety, interpretability and interactivity. I have rich experience on building learning-based/data-driven controllers for autonomous vehicles, legged robots and drones.


News

Sep, 2022 I am looking for PhD position outside of the US
Sep, 2022 Policy Dissection is to appear in NeurIPS22 :blush:
Mar, 2022 I am so happy that MetaDrive is finally accepted to TPAMI :sob:.

Publications (* indicates joint first author)

  1. NeurIPS
    Human-AI Shared Control via Frequency-based Policy Dissection
    Quanyi, Li and Zhenghao Peng, Haibin Wu, Lan Feng, and Bolei Zhou
    In Advances in Neural Information Processing Systems (NeurIPS) , 2022
  2. TPAMI
    MetaDrive: Composing Diverse Driving Scenarios for Generalizable Learning
    Quanyi, Li* and Zhenghao Peng*, Lan Feng, Qihang Zhang, Zhenghai Xue, and Bolei Zhou
    In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) , 2022
  3. ICLR
    Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization
    Quanyi, Li* and Zhenghao Peng*, and Bolei Zhou
    In International Conference on Learning Representations (ICLR) , 2022
  4. NeurIPS
    Learning to Simulate Self-driven Particles System with Coordinated Policy Optimization
    Zhenghao Peng, Quanyi, Li and Chunxiao Liu, and Bolei Zhou
    In Advances in Neural Information Processing Systems (NeurIPS) , 2021
  5. CoRL
    Safe Driving via Expert Guided Policy Optimization
    Zhenghao Peng*, Quanyi, Li* and Chunxiao Liu, and Bolei Zhou
    In 5th Annual Conference on Robot Learning (CoRL) , 2021
  6. CVPR workshop
    Improving the Generalization of End-to-End Driving through Procedural Generation
    Quanyi, Li* and Zhenghao Peng*, Qihang Zhang, Chunxiao Liu, and Bolei Zhou
    In CVPR embodied AI workshop (CVPR workshop) , 2021
  7. IoTJ
    Reinforcement-learning-and belief-learning-based double auction mechanism for edge computing resource allocation
    Quanyi, Li and Haipeng Yao, Tianle Mai, Chunxiao Jiang, and Yan Zhang
    IEEE Internet of Things Journal (IoTJ) , 2019

Services

Conference Reviewer: ICML 2022, NeurIPS 2022, CoRL 2022