Chengshu (Eric) Li
I am currently a fourth-year Ph.D. student in Computer Science at Stanford University. I am advised by Prof. Fei-Fei Li and Prof. Silvio Savarese at the Stanford Vision and Learning Lab. My research interest lies at robot learning and 3D simulation environment.
I received my B.S. in Computer Science with Distinction from Stanford University in 2017 and M.S. in Management Science & Engineering from Stanford University in 2020. In the past, I've worked/interned at Google Deepmind (robotics team) (2023), Nvidia (2022-2023), Google Brain Robotics (2019-2020), AutoX (2017-2018), Shift (2016), and Tableau (2015).
Email: chengshu@stanford.edu
News
2024/05/01: Our paper Chain of Code: Reasoning with a Language Model-Augmented Code Emulator is accepted at ICML 2024 (Oral)!
2024/03/18: We presented the long-awaited full release of BEHAVIOR-1K at GTC 2024. Watch our talk (free registration) here! Check out our website!
2023/12/08: We released Chain of Code: Reasoning with a Language Model-Augmented Code Emulator!
2022/09/10: Our paper BEHAVIOR-1K: A Benchmark for Embodied AI with 1,000 Everyday Activities and Realistic Simulation is accepted at CoRL 2022 and nominated for best paper!
2021/09/13: Our papers BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments and iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks are accepted at CoRL 2021!
2021/06/30: Our paper iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenes is accepted at IROS 2021!
2021/06/20: We concluded the iGibson Challenge 2021 and the CVPR2021 Embodied AI Workshop. Check out our video for the challenge and the panel discussions that I was a part of!
2021/02/28: Our paper ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation is accepted at ICRA 2021!
2021/02/17: We launched the iGibson Challenge 2021 at the CVPR2021 Embodied AI Workshop! We featured Interactive and Social Navigation in dynamic environments in iGibson!
Education
Stanford University
Ph.D. Candidate in Computer Science
2020/09 - Present
Stanford, CA
Stanford University
Master of Science in Management Science and Engineering
2019/01 - 2020/06
Stanford, CA
GPA: 4.0 / 4.0
Stanford University
Bachelor of Science in Computer Science with Distinction
2013/09 - 2017/06
Stanford, CA
GPA: 3.93 / 4.0
Publications (First-Author/Co-First Author)
* denotes equal contribution
* denotes equal contribution
Chain of Code: Reasoning with a Language Model-Augmented Code Emulator
BEHAVIOR-1K: A Benchmark for Embodied AI with 1,000 Everyday Activities and Realistic Simulation
Chengshu Li*, Ruohan Zhang*, Josiah Wong*, Cem Gokmen*, Sanjana Srivastava*, Roberto Martín-Martín*, Chen Wang*, Gabrael Levine*, Michael Lingelbach, Jiankai Sun, Mona Anvari, Minjune Hwang, Manasi Sharma, Arman Aydin, Dhruva Bansal, Samuel Hunter, Kyu-Young Kim, Alan Lou, Caleb R Matthews, Ivan Villa-Renteria, Jerry Huayang Tang, Claire Tang, Fei Xia, Silvio Savarese, Hyowon Gweon, Karen Liu, Jiajun Wu, Li Fei-Fei
Conference on Robot Learning (CoRL) 2022 (Oral)
Nominated for Best Paper Award
[paper][arxiv paper][website][code]
BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments
iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks
iGibson 1.0: A Simulation Environment for Interactive Tasks in Large Realistic Scenes
Bokui Shen*, Fei Xia*, Chengshu Li*, Roberto Martín-Martín*, Linxi Fan, Guanzhi Wang, Claudia Pérez-D'Arpino, Shyamal Buch, Sanjana Srivastava, Lyne Tchapmi, Micael Tchapmi, Kent Vainio, Josiah Wong, Li Fei-Fei, Silvio Savarese
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2021
Publications (Other)
BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation
Yunhao Ge*, Yihe Tang*, Jiashu Xu*, Cem Gokmen*, Chengshu Li, Wensi Ai, Benjamin Jose Martinez, Arman Aydin, Mona Anvari, Ayush K Chakravarthy, Hong-Xing Yu, Josiah Wong, Sanjana Srivastava, Sharon Lee, Shengxin Zha, Laurent Itti, Yunzhu Li, Roberto Martín-Martín, Miao Liu, Pengchuan Zhang, Ruohan Zhang, Li Fei-Fei, Jiajun Wu
Conference on Computer Vision and Pattern Recognition (CVPR) 2024
[paper]
Modeling Dynamic Environments with Scene Graph Memory
Andrey Kurenkov, Michael Lingelbach, Agarwal Tanmay, Chengshu Li, Emily Jin, Li Fei-Fei, Jiajun Wu, Silvio Savarese, Roberto Martín-Martín
International Conference on Machine Learning (ICML) 2023
[paper]
Task-Driven Graph Attention for Hierarchical Relational Object Navigation
Michael Lingelbach, Chengshu Li, Minjune Hwang, Andrey Kurenkov, Alan Lou, Roberto Martín-Martín, Ruohan Zhang, Li Fei-Fei, Jiajun Wu
IEEE International Conference on Robotics and Automation (ICRA) 2023
[paper]
SONICVERSE: A Multisensory Simulation Platform for Embodied Household Agents that See and Hear
Ruohan Gao*, Hao Li*, Gokul Dharan, Zhuzhu Wang, Chengshu Li, Fei Xia, Silvio Savarese, Li Fei-Fei, Jiajun Wu
IEEE International Conference on Robotics and Automation (ICRA) 2023
[paper]
Eye-BEHAVIOR: An Eye-Tracking Dataset for Everyday Household Activities in Virtual, Interactive, and Ecological Environments
Cem Gokmen, Ruohan Zhang, Sanjana Srivastava, Chengshu Li, Michael Lingelbach, Roberto Martín-Martín, Silvio Savarese, Jiajun Wu, Li Fei-Fei
Journal of Vision December 2022, Volume 22, Issue 14, 3819
[paper]
Interactive Gibson Benchmark (iGibson 0.5): A Benchmark for Interactive Navigation in Cluttered Environments
Fei Xia, William B. Shen, Chengshu Li, Priya Kasimbeg, Micael Tchapmi, Alexander Toshev, Roberto Martín-Martín, Silvio Savarese
IEEE Robotics and Automation Letters (RA-L) and International Conference on Robotics and Automation (ICRA) 2020
Principles and Guidelines for Evaluating Social Robot Navigation Algorithms
Anthony Francis, Claudia Pérez-d'Arpino, Chengshu Li, Fei Xia, Alexandre Alahi, Rachid Alami, Aniket Bera, Abhijat Biswas, Joydeep Biswas, Rohan Chandra, Hao-Tien Lewis Chiang, Michael Everett, Sehoon Ha, Justin Hart, Jonathan P How, Haresh Karnan, Tsang-Wei Edward Lee, Luis J Manso, Reuth Mirksy, Soeren Pirk, Phani Teja Singamaneni, Peter Stone, Ada V Taylor, Peter Trautman, Nathan Tsoi, Marynel Vazquez, Xuesu Xiao, Peng Xu, Naoki Yokoyama, Alexander Toshev, Roberto Martín-Martín
arXiv pre-print
[paper]
Retrospectives on the Embodied AI Workshop
Matt Deitke, Dhruv Batra, Yonatan Bisk, Tommaso Campari, Angel X Chang, Devendra Singh Chaplot, Changan Chen, Claudia Pérez D'Arpino, Kiana Ehsani, Ali Farhadi, Li Fei-Fei, Anthony Francis, Chuang Gan, Kristen Grauman, David Hall, Winson Han, Unnat Jain, Aniruddha Kembhavi, Jacob Krantz, Stefan Lee, Chengshu Li, Sagnik Majumder, Oleksandr Maksymets, Roberto Martín-Martín, Roozbeh Mottaghi, Sonia Raychaudhuri, Mike Roberts, Silvio Savarese, Manolis Savva, Mohit Shridhar, Niko Sünderhauf, Andrew Szot, Ben Talbot, Joshua B Tenenbaum, Jesse Thomason, Alexander Toshev, Joanne Truong, Luca Weihs, Jiajun Wu
arXiv pre-print
[paper]
Gibson Env V2: Embodied Simulation Environments for Interactive Navigation
Fei Xia, Chengshu Li, Kevin Chen, Bokui Shen, Roberto Martín-Martín, Noriaki Hirose, Amir R. Zamir, Li Fei-Fei, Silvio Savarese
Deep Learning for Semantic Visual Navigation Workshop @ CVPR 2019
[paper]
Industry Experience
Google Deepmind (robotics team)
Student Researcher
2023/06 - 2023/11
Mountain View, CA
NVIDIA Corporation
Research Intern (Part-time)
2022/01 - 2023/01
Santa Clara, CA
Google Brain Robotics
Student Researcher (Part-time)
2019/11 - 2020/05
Mountain View, CA
AutoX, Inc.
Research Engineer for Deep Learning and Perception
2017/09 - 2018/12
San Jose, CA
Shift Technologies, Inc.
Software Engineering Intern
2016/06 - 2016/09
San Francisco, CA
Tableau Software
Software Engineering Intern
2015/06 - 2015/09
Seattle, WA
Tech Reports
Indexed Value Function Learning via Distributional Temporal Difference
Tian Tan*, Zhihan Xiong*, Chengshu Li*
[paper]
DeepShuai: Deep Reinforcement Learning based Chinese Chess Player
Chengshu Li*, Kedao Wang*, Zihua Liu*
[paper]
Effective Word Representation for Named Entity Recognition
Jun-Ting Hsieh*, Chengshu Li*, Wendi Liu*
[paper]
