Zhaojing's Homepage

Zhaojing Yang

[CV] [Google Scholar] [GitHub] [X] [LinkedIn]

Hi! I'm a Research Engineer at Meta Superintelligence Labs (MSL). Previously I was a Founding Research Engineer at Assured Robot Intelligence (ARI). My research focuses on Robot Learning to bring humanoid robots to real-world applications.

I've been fortunate to work with Prof. Xiaolong Wang at UCSD, and with Prof. Erdem Bıyık and Prof. Gaurav Sukhatme at USC. I received my MSCS degree from USC and my BEng degree in Computer Science from Shanghai Jiao Tong University.

News

[May, 2026] I joined MSL following Meta's acquisition of ARI.
[Jan, 2026] Our paper on Learning from Constrained Demonstrators was accepted to ICLR 2026. Congrats to Xinhu and the team!
[Oct, 2025] Our paper on Active Reward Learning from Language Feedback was accepted to IJRR. Congrats to Eisuke and the team!
[May, 2025] I joined ARI as a founding research engineer.
[Apr, 2025] NaVILA was accepted to RSS 2025. See you in Los Angeles!
[Oct, 2024] Our paper on Learning from Comparative Language Feedback was accepted to CoRL 2024!
[Jan, 2024] Our paper on Quadrotors Collision Avoidance and Local Navigation was accepted to ICRA 2024!

Publications

* denotes equal contribution, † denotes equal advising

NaVILA: Legged Robot Vision-Language-Action Model for Navigation
An-Chieh Cheng^*, Yandong Ji^*, Zhaojing Yang^*, Zaitian Gongye, Xueyan Zou, Jan Kautz, Erdem Bıyık, Hongxu Yin^†, Sifei Liu^†, Xiaolong Wang^†
RSS 2025
[Paper] [VLA Code] [Locomotion Code] [Website]

Trajectory Improvement and Reward Learning from Comparative Language Feedback
Zhaojing Yang, Miru Jun, Jeremy Tien, Stuart Russell, Anca Dragan, Erdem Bıyık
HRI 2024 Human-Interactive Robot Learning Workshop
CoRL 2024
[Paper] [Code] [Website]

Collision Avoidance and Navigation for a Quadrotor Swarm Using End-to-end Deep Reinforcement Learning
Zhehui Huang^*, Zhaojing Yang^*, Rahul Krupani, Baskın Şenbaşlar, Sumeet Batra, Gaurav S. Sukhatme
ICRA 2024
[Paper] [Code] [Website]

When a Robot is More Capable than a Human: Learning from Constrained Demonstrators
Xinhu Li, Ayush Jain, Zhaojing Yang, Yigit Korkmaz, Erdem Bıyık
ICLR 2026
[Paper] [arXiv] [Website]

Active Reward Learning and Iterative Trajectory Improvement from Comparative Language Feedback
Eisuke Hirota^*, Zhaojing Yang^*, Ayano Hiranaka, Miru Jun, Jeremy Tien, Stuart Russell, Anca Dragan, Erdem Bıyık
IJRR
[Paper] [Code] [Website]

NaVILA: Legged Robot Vision-Language-Action Model for Navigation
An-Chieh Cheng^*, Yandong Ji^*, Zhaojing Yang^*, Zaitian Gongye, Xueyan Zou, Jan Kautz, Erdem Bıyık, Hongxu Yin^†, Sifei Liu^†, Xiaolong Wang^†
RSS 2025
[Paper] [VLA Code] [Locomotion Code] [Website]

Trajectory Improvement and Reward Learning from Comparative Language Feedback
Zhaojing Yang, Miru Jun, Jeremy Tien, Stuart Russell, Anca Dragan, Erdem Bıyık
HRI 2024 Human-Interactive Robot Learning Workshop
CoRL 2024
[Paper] [Code] [Website]

Collision Avoidance and Navigation for a Quadrotor Swarm Using End-to-end Deep Reinforcement Learning
Zhehui Huang^*, Zhaojing Yang^*, Rahul Krupani, Baskın Şenbaşlar, Sumeet Batra, Gaurav S. Sukhatme
ICRA 2024
[Paper] [Code] [Website]

QuadSwarm: A Modular Multi-Quadrotor Simulator for Deep Reinforcement Learning with Direct Thrust Control
Zhehui Huang, Sumeet Batra, Tao Chen, Rahul Krupani, Tushar Kumar, Artem Molchanov, Aleksei Petrenko, James Alan Preiss, Baskın Şenbaşlar, Zhaojing Yang, Gaurav S. Sukhatme
ICRA 2023 The Role of Robotics Simulators for Unmanned Aerial Vehicles Workshop
[Paper] [Code]