Jason (Xue Bin) Peng
About
Appointed Canada CIFAR AI Chair – 2026
Xue Bin’s work focuses on developing machine learning techniques that enable artificial agents to replicate the motor capabilities of humans and animals, with applications in computer graphics and robotics. He has developed motion imitation methods that enable simulated characters and real-world robots to replicate a broad spectrum of human behaviors, ranging from common everyday locations, such as walking and running, to highly athletic skills, such as acrobatics and martial arts. To transfer techniques developed in simulation to real-world robots, he has also developed sim-to-real transfer methods that enable controllers trained in simulation to be deployed on robots operating in the real world.
Awards
- Early Career Research Award, CHCCS/SCDHM Graphics Interface (2024)
- Outstanding Doctoral Dissertation Award, ACM SIGGRAPH (2022)
- Best Paper Award, Robotics: Science and Systems (2020)
- Postgraduate Scholarship – Doctoral Program, NSERC (2017)
- Governor General’s Gold Medal, Governor General of Canada (2017)
Relevant Publications
- Peng, X. B., Guo, Y., Halper, L., Levine, S., & Fidler, S. (2022). “ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters.” ACM Transactions on Graphics.
- Peng, X. B., Ma, Z., Abbeel, P., Levine, S., & Kanazawa, A. (2021). “AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control.” ACM Transactions on Graphics.
- Peng, X. B., Coumans, E., Zhang, T., Lee, T. W., Tan, J., Levine, S. (2020). “Learning Agile Robotic Locomotion Skills by Imitating Animals.” Robotics: Science and Systems.
- Peng, X. B., Abbeel, P., Levine, S., & van de Panne, M. (2018). “DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills.” ACM Transactions on Graphics.
- Peng, X. B., Andrychowicz, M., Zaremba, W., & Abbeel, P. (2018). “Sim-to-Real Transfer of Robotic Control with Dynamics Randomization.” IEEE International Conference on Robotics and Automation.