LI Yikang's Homepage

AI Investor @ IDG Capital.
Level 41, Jing An Kerry Centre, Jingan District, Shanghai, China [at]
Google scholar | Github || LinkedIn || Resume | 中文简历 (deprecated)

I am currently embracing an exhilarating journey as an AI Investor at IDG Capital, where since August 2022, I have been nurturing advancements in domains like Generative AI, Autonomous Driving, Robotics, Large Language Models, and their associated supply chains and applications. My primary focus is on fostering innovation and driving the surge of technology to new frontiers.

Prior to my current role, I was the Founder of ADLab @ Shanghai AI Lab. I built a research team consisting of 40+ talented researchers and interns aiming at revolutionizing the transportation system in a data-driven way.

Before that, I worked as Deputy Director of R&D at Sensetime Technology Ltd, leading a product team containing over 30 talented engineers and product specialists, developing the RoboX Autonomous Products, including RoboBus & RoboSweeper.

In May 2020, I acquired my Ph.D. from The Chinese University of Hong Kong under the esteemed guidance of Professors Xiaogang Wang and Xiaoou Tang. I got my bachelor’s degrees of Electronic Engineering and Economics in Tsinghua University in 2016. During my doctoral years, I garnered invaluable experience working as a research intern at Microsoft Research Asia (MSRA) and Meta Reality Labs (formerly Facebook Reality Labs).

Research Interests: My academic pursuits gravitate towards 3D Scene Reconstruction, 3D Scene Perception, Behaviour & Scene Simulation, and an extensive range of topics related to Autonomous Driving.

***Connect & Collaborate*** 
I am always eager to foster collaborations and new ventures. If you are passionate about forging your business path or joining a startup in the realms we share interests in, I invite you to reach out. Let’s exchange visionary insights over a cup of coffee.


Jul 13, 2023 4 Papers are accepted by ICCV-23.  NEW!
Feb 28, 2023 6 Papers are accepted by CVPR-23.
Jan 17, 2023 2 Papers are accepted by ICRA-23, Sensor Calibration * 1 and Sensor Placement * 1.
Nov 20, 2022 One paper is accepted by AAAI-23, Instance Segmentation for Autonomous Driving.
Jul 4, 2022 Two papers are accepted by ECCV-2022, sensor fusion * 1 and NeRF * 1.
Jul 1, 2022 I have finished all the handovers at Sensetime. I am really grateful for the 3-year unforgettable experience here.

Selected publications

  1. ECCV
    L-Tracing: Fast Light Visibility Estimation on Neural Surfaces by Sphere Tracing
    Ziyu Chen, Chenjing Ding, Jianfei Guo, Dongliang Wang, Yikang Li , Xuan Xiao, Wei Wu, and Li Song
    European Conference on Computer Vision 2022
  2. ECCV
    Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection
    Xin Li, Botian Shi, Yuenan Hou, Xingjiao Wu, Tianlong Ma, Yikang Li# , and Liang He
    European Conference on Computer Vision 2022
  3. IROS
    CROON: Automatic Multi-LiDAR Calibration and Refinement Method in Road Scene
    Pengjin Wei, Guohang Yan, Yikang Li , Kun Fang, Wei Liu, Xinyu Cai, and Jie Yang
    International Conference on Intelligent Robots and Systems 2022
  4. ITSC
    General Driving Behavior Model based on the Desired Safety Margin for Vehicle Flow Simulation
    Pinlong Cai, Junjie Zhang, Xuan Zhao, and Yikang Li#
    International Conference on Intelligent Transportation Systems 2022
  5. CVPR
    β-DARTS: Beta-Decay Regularization for Differentiable Architecture Search
    Peng Ye, Baopu Li, Yikang Li , Tao Chen, Jiayuan Fan, and Wanli Ouyang
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022
  6. CVPR
    Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation
    Yuenan Hou, Xinge Zhu, Yuexin Ma, Chen Change Loy, and Yikang Li#
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022
  7. NeurIPS
    Pastegan: A Semi-parametric Method to Generate Image from Scene Graph
    Yikang Li , Tao Ma, Yeqi Bai, Nan Duan, Sining Wei, and Xiaogang Wang
    Advances in Neural Information Processing Systems (NeurIPS) 2019
  8. ECCV
    Factorizable Net: an Efficient Subgraph-based Framework for Scene Graph Generation
    Yikang Li , Wanli Ouyang, Bolei Zhou, Jianping Shi, Chao Zhang, and Xiaogang Wang
    Proceedings of the European Conference on Computer Vision (ECCV) 2018
  9. CVPR
    Visual Question Generation as Dual Task of Visual Question Answering
    Yikang Li , Nan Duan, Bolei Zhou, Xiao Chu, Wanli Ouyang, Xiaogang Wang, and Ming Zhou
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2018
  10. ICCV
    Scene Graph Generation from Objects, Phrases and Region Captions
    Yikang Li , Wanli Ouyang, Bolei Zhou, Kun Wang, and Xiaogang Wang
    Proceedings of the IEEE International Conference on Computer Vision (ICCV) 2017
  11. CVPR
    ViP-CNN: Visual Phrase Guided Convolutional Neural Network
    Yikang Li , Wanli Ouyang, and Xiaogang Wang
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2017
  1. Arxiv
    OpenCalib: A Multi-sensor Calibration Toolbox for Autonomous Driving
    Guohang Yan, Zhuochun Liu, Chengjie Wang, Chunlei Shi, Pengjin Wei, Xinyu Cai, Tao Ma, Zhizheng Liu, Zebin Zhong, Yuqian Liu, Ming Zhao, Zheng Ma, and Yikang Li#
    arXiv preprint arXiv:2205.14087 2022
  2. Arxiv
    Joint Camera Intrinsic and LiDAR-Camera Extrinsic Calibration
    Guohang Yan, Feiyu He, Chunlei Shi, Xinyu Cai, and Yikang Li#
    arXiv preprint arXiv:2202.13708 2022
  3. Arxiv
    Multi-modal Sensor Fusion for Auto Driving Perception: A Survey
    Keli Huang, Botian Shi, Xiang Li, Xin Li, Siyuan Huang, and Yikang Li#
    arXiv preprint arXiv:2202.02703 2022
  4. Arxiv
    Perception Entropy: A Metric for Multiple Sensors Configuration Evaluation and Design
    Tao Ma, Zhizheng Liu, and Yikang Li#
    arXiv preprint arXiv:2104.06615 2021
  5. Arxiv
    CRLF: Automatic Calibration and Refinement based on Line Feature for LiDAR and Camera in Road Scenes
    Tao Ma, Zhizheng Liu, Guohang Yan, and Yikang Li#
    arXiv preprint arXiv:2103.04558 2021
HTML Hit Counters