Shuo Yang

I am a Ph.D. candidate at the University of Pennsylvania GRASP Lab, advised by Professor George J. Pappas. I obtained my Bachelor's degree (Summa Cum Laude) from Shanghai Jiao Tong University in 2021 where I worked closely with Professor Xiang Yin. I have spent time in both tech (Toyota Research, Tencent AI) and quant finance (Point72/Cubist).

My past research focuses on ensuring the safety of AI-enabled robots, allowing them to complete complex tasks while remaining robust to real-world uncertainty. My research draws on tools from formal methods, statistics, and game theory. I am particularly interested in the following areas:

• Safe, adaptive and efficient (reinforcement & imitation) learning-based control in (mainly non-cooperative) multi-agent systems
• Efficient policy learning (e.g. diffusion policy) for robotics control
• Uncertainty-aware safe control for learning-enabled systems (e.g. using conformal prediction)
• Formal verification and synthesis for learning-enabled systems

Email  /  Linkedin /  Github  /  Google Scholar  /  GRASP Page

(* indicates equal contribution, see full list on Google Scholar)

Dynamic Rank Adjustment in Diffusion Policies for Efficient and Flexible Training
Xiatao Sun, Shuo Yang, Yinxing Chen, Francis Fan, Yiyan (Edgar) Liang, Daniel Rakita
Robotics: Science and Systems (RSS) 2025 [webpage][arxiv][code]

Key words: Online Imitation Learning, Diffusion Model

Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specifications
Jiangwei Wang, Shuo Yang, Ziyan An, Songyang Han, Zhili Zhang, Rahul Mangharam, Meiyi Ma, Fei Miao
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2025 [arxiv]

Key words: Reinforcement Learning, Multi-Agent Systems, Safety

STLGame: Signal Temporal Logic Games in Adversarial Multi-Agent Systems
Shuo Yang, Hongrui Zheng, Cristian-Ioan Vasile, George J. Pappas, Rahul Mangharam
Learning for Dynamics & Control Conference (L4DC) 2025 [webpage][arxiv][code]

Key words: Multi-Agent Systems, Game Theory, Formal Methods

MEGA-DAgger: Imitation Learning with Multiple Imperfect Experts
Xiatao Sun*, Shuo Yang*, Mingyan Zhou, Kunpeng Liu, Rahul Mangharam
IEEE International Conference on Intelligent Transportation Systems (ITSC) 2024 [arxiv][code]

Key words: Imitation Learning, Autonomous Racing, Safety

Learning Adaptive Safety for Multi-Agent Systems
Luigi Berducci, Shuo Yang, Rahul Mangharam, Radu Grosu
IEEE International Conference on Robotics and Automation (ICRA) 2024 [arxiv][code]

Key words: Reinforcement Learning, Multi-Agent Systems, Safety

Safe Perception-based Control under Stochastic Sensor Uncertainty using Conformal Prediction
Shuo Yang, George J. Pappas, Rahul Mangharam, Lars Lindemann
IEEE Conference on Decision and Control (CDC) 2023 [arxiv]

Key words: Safety, Uncertainty Quantification, Perception

Secure Your Intention: On Notions of Pre-Opacity in Discrete-Event Systems
Shuo Yang, Xiang Yin
IEEE Transactions on Automatic Control (TAC) 2022 [arxiv]

Key words: Information Privacy, Automata Theory

• 2024, L-CSS Outstanding Reviewer Award (top 1%) [Letter]
• 2024, DAAD AInet Fellow (Safe and Secure AI)
• 2023, ACC Travel Grant
• 2021, The Dean's Fellowship from Penn
• 2021, Solomon M. Swaab Fellowship from Penn
• 2021, Outstanding Graduate of SJTU
• 2021, Outstanding Bachelor Thesis Award from SJTU (top 1%)
• 2020, Person of the Year of SJTU [SJTU News Spotlight]
• 2018 & 2019, Outstanding Academic Scholarship from SJTU

• Co-organizer: the 2nd Workshop on MAD-Games: Multi-Agent Dynamic Games @ ICRA 2024
• Area Chair: Tiny Papers @ ICLR 2024, 2023
• I also serve as a CPHS'2024 mentor.
• Reviewer:
  • American Control Conference (ACC)
  • IEEE Conference on Decision and Control (CDC)
  • International Conference on Cyber-Physical Systems (ICCPS)
  • Advances in Neural Information Processing Systems (NeurIPS)
  • AAAI Conference on Artificial Intelligence (AAAI)
  • IEEE Transactions on Automatic Control (TAC)
  • IEEE Robotics and Automation Letters (RA-L)
  • IEEE Control Systems Letters (L-CSS)
  • IEEE Transactions on Intelligent Vehicles (TIV)
  • Nonlinear Analysis: Hybrid Systems (NAHS)
  • IEEE International Conference on Robotics and Automation (ICRA)
  • IROS 2023 Workshop on Multi-agent Dynamic Games (MAD-Games)
  • NeurIPS 2023 AI for Science Workshop (AI4Science)
  • etc.

Template from here.
Last updated Aug 2025.