Ming Jin

I am an assistant professor in the Bradley Department of Electrical and Computer Engineering at Virginia Tech. I am also affiliated with the Power and Energy Center, Autonomy and Robotics @ VT, and a core faculty of the Sanghani Center for Artificial Intelligence and Data Analytics.

I work on trustworthy AI, safe reinforcement learning, foundation models, with applications for power systems, recommender systems, and control systems.

I received my PhD in Electrical Engineering and Computer Science from UC Berkeley and BEng (honors) in Electronic and Computer Engineering from the Hong Kong University of Science and Technology. I was a postdoc in Industrial Engineering and Operations Research at UC Berkeley.

  ·     ·  


Research interests

Services and Outreach

  • AC/SPC of ICML 2024, AAAI 2025
  • Associate Editor of IEEE Systems Journal
  • Safe Reinforcement Learning Tutorial @ IJCAI 2024 (Slides)
  • Trustworthy Interactive Decision-Making with Foundation Models Workshop @ IJCAI 2024
  • Safe RL for power systems Tutorial and Workshop @ SmartGridComm 2024 (Slides)
  • Distributed Control and Machine Learning for Power Systems Tutorial @ SmartGridComm 2024 (Slides)
  • Safe Reinforcement Learning Online Seminar (Website)

Selected Awards

  • 1st Place Winner of the 2021 CityLearn Challenge (2021)
  • Siebel Scholar (class of 2018)
  • Best paper award, Building and Environment (2018)
  • Best paper runner-up award at EAI MobiQuitous (2016)
  • Best paper award at UBICOMM (2015)



News

August 2024

Safe Reinforcement Learning tutorial at IJCAI 2024 Slides

Mar 2024

Join us at IJCAI 2024 Workshop on Trustworthy Interactive Decision Making with Foundation Models (Call for Contributions)

Jan 2024

Our project on LLMs for Supply Chain Cybersecurity, in collaboration with Prof. Peter Beling, has been selected for support by Commonwealth Cyber Initiative (CCI).

Nov 2023

Our project on safe RL for power systems, in collaboration with Prof. Javad Lavaei, has been selected for support by NSF under the Safe Learning-Enabled System Program.

Aug 2023

Our project on Safe RL for Interactive Systems with Stakeholder Alignment has been selected for support by Amazon-VT Initiative in Efficient and Robust Machine Learning.

Aug 2023

Paper on Optimization Autoformalism that uses large language models to craft optimization solutions for decision-making

Mar 2023

Paper on certified robustness for neural ODE accepted in IEEE Control Systems Letters (L-CSS)

Mar 2023

Paper on derivative-free meta blackbox (nonconvex) optimization on manifold at L4DC 2023 (oral presentation)

... see all News