I am a postdoctoral associate at University of Maryland, College Park working with Furong Huang and Tom Goldstein. I obtained my Ph.D. from Electrical and Computer Engineering at the University of California, Riverside, under the guidance of M. Salman Asif. Originally from Wuhan, the "River City" of China, I completed my B.S. in Automation at Wuhan University of Technology.

My research focuses on trustworthy machine learning, where I strive to identify vulnerabilities / limitations and enhance the trustworthiness (robustness, safety, privacy, and more) of machine learning systems. Besides model level trustworthiness, I also build embodied and agentic systems that can reason, act, and adapt responsibly inside the physical environment.

Current interests:

  • Multi-modal reasoning across vision, language, and action [ MORSE-500 ]
  • Building AI agents that plan, act, and self-improve
  • Embodied AI for navigation and manipulation in robotics
  • Agentic safety and alignment in multi-agent ecosystems [ AegisLLM ]
  • Controllable and safe AI via model editing and unlearning [ SLUG, Robust Eval ]
Previous experience: In the past, I was fortunate to have interned at UII America (Summer 2022 in Cambridge, MA), working with Benjamin Planche and Ziyan Wu; and at PARC (Summer 2021 in Palo Alto, CA) working with Shantanu Rane.

News