Tao Huang - 黄涛

taohuang.jpg

at Lamma Island in 2023

I am a final-year M.Phil. student in Computer Science and Engineering at The Chinese University of Hong Kong advised by Qi Dou. Before joining CUHK, I obtained my B.Eng. degree at ShanghaiTech as Outstanding Graduate in Shanghai. I have spent a wonderful summer in Tencent Robotics X. Currently, I am working with Huazhe Xu at Shanghai Qi Zhi Institute and Jiangmiao Pang at Shanghai AI Laboratory.

My research aims to build intelligent machines through reinforcement learning (for achieving higher sampler efficiency) and robot learning (for improving long-horizon reasoning ability) from their experiences and offline data in the physical world. Outside of academics, I am an enthusiast of street photography.


Recent Activities

Mar 24, 2024 One paper on physics-based scene/motion generation was accepted to SIGGRAPH 2024.
Dec 22, 2023 One preprint on reward learning for robotic RL tasks (Diffusion Reward) was released.
Jun 22, 2023 One paper on RL for long-horizon robotic tasks (ViSkill) was accepted to IROS 2023.
May 19, 2023 One paper on robot learning platform (SurRoL) was accepted to RA-L 2023.
Jan 16, 2023 One paper on data-efficient RL for robotic tasks (DEX) was accepted to ICRA 2023.
Aug 1, 2022 I start to pursuing M.Phil. degree at CUHK.

Selected Projects

  1. SIGGRAPH
    Physics-based Scene Layout Generation from Human Motion
    Jianan Li, Tao Huang, Qingxu Zhu, and Tien-Tsin Wong
    ACM SIGGRAPH (SIGGRAPH) , 2024
    Details
  2. Under Review
    Diffusion Reward: Learning Rewards via Conditional Video Diffusion
    Tao Huang*, Guangqi Jiang*, Yanjie Ze, and Huazhe Xu
    (Under Review) , 2023
    Details
  3. IROS
    Value-Informed Skill Chaining for Policy Learning of Long-Horizon Tasks with Surgical Robot
    Tao Huang, Kai Chen, Wang Wei, Jianan Li, Yonghao Long, and Qi Dou
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , 2023
    Details
  4. ICRA
    Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot
    Tao Huang, Kai Chen, Bin Li, Yun-Hui Liu, and Qi Dou
    International Conference on Robotics and Automation (ICRA) , 2023
    Details
  5. RA-L
    Human-in-the-loop Embodied Intelligence with Interactive Simulation Environment for Surgical Robot Learning
    Yonghao Long, Wang Wei, Tao Huang, Yuehao Wang, and Qi Dou
    Robotics and Automation Letters (RA-L) , 2023
    Details
  6. ICC
    Learning-Aided Stable Matching for Switch-Controller Association in SDN Systems
    Yinxu Tang, Tao Huang, Xi Huang, Ziyu Shao, and Yang Yang
    International Conference on Communications (ICC) , 2022
    Details
  7. Preprint
    Accelerating Representation Learning with View-Consistent Dynamics in Data-Efficient Reinforcement Learning
    Tao Huang*, Jiachen Wang*, and Xiao Chen
    arXiv preprint arXiv:2201.07016 (Preprint) , 2022
    Details