Bokui (William) Shen 沈博魁

willshen at cs dot stanford dot edu [Github] [Google Scholar] [LinkedIn] [CV]

About me

I am a CS Ph.D. candidate at Stanford University. My research interests lie in computer vision and robot learning. I received a B.S. in computer science, with Departmental Honor and University Distinction, from Stanford University.


  • iGibson, a Simulation Environment for Interactive Tasks in Large Realistic Scenes
    [project] [PDF] [code]

  • Bokui Shen*, Fei Xia*, Chengshu Li*, Roberto Martín-Martín*, Linxi Fan, Guanzhi Wang, Shyamal Buch, Claudia D'Arpino, Sanjana Srivastava, Lyne P. Tchapmi, Micael E. Tchapmi, Kent Vainio, Li Fei-Fei, Silvio Savarese

  • IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021).

  • Fully interactive simulation environment with fast visual rendering and physics simulation.

  • Interactive Gibson: A Benchmark for Interactive Navigation in Cluttered Environments
    [project] [PDF]

  • Fei Xia, Bokui Shen, Chengshu Li, Priya Kasimbeg, Micael Tchapmi, Alexander Toshev, Roberto Martín-Martín, Silvio Savarese.

  • IEEE Robotics and Automation Letters (RA-L) and ICRA, 2020.

  • The first comprehensive benchmark for training and evaluating Interactive Navigation .

  • Situational Fusion of Visual Representation for Visual Navigation
    [project] [PDF]

  • Bokui Shen, Danfei Xu, Yuke Zhu, Leonidas Guibas, Li Fei-Fei, Silvio Savarese.

  • ICCV, 2019.

  • Learning generalizable navigation policy from mid-level visual representations.

  • Taskonomy: Disentangling Task Transfer Learning
    [project] [code] [Blog Post in Chinese (知乎)]

  • Amir R. Zamir, Bokui Shen*, Alexander Sax*, Leonidas Guibas, Jitendra Malik, Silvio Savarese. (*equal)

  • CVPR, Best Paper 2018

  • Leveraging task space structure to optimize supervision policy of a set of tasks.

  • Visual Forecasting by Imitating Dynamics in Natural Sequences

  • Kuo-Hao Zeng, Bokui Shen, De-An Huang, Min Sun, Juan Carlos Niebles.

  • ICCV, Spotlight 2017.

  • General framework for visual forecasting using inverse reinforcement learning (IRL).

  • Feedback networks
    [project] [code]

  • Amir R. Zamir*, Te-lin Wu*, Lin Sun, Bokui Shen, Jitendra Malik, Silvio Savarese.

  • CVPR, 2017

  • Feedback network paradigm with early prediction, taxonomic compliance and curriculum-based learning.

(*Equally contributed to the project and alphabetically listed)

Honors and Awards


Sep. 2018 - Present, Department of Computer Science, Stanford University,

PhD in CS

IEEE-CVPR 2018 Best Paper Award, Qualcomm Innovation Fellowship

Sep. 2014 - Jun. 2018, Department of Computer Science, Stanford University,

Undergraduate Student. GPA: 4.0/4.0

Terman Award, CS Department Honor, University Distinction



© William Shen 2017