I am a Postdoctoral Researcher at the Dynamics, Sensing and Controls Laboratory, University of Connecticut, working under the mentorship of Professor Jiong Tang. I earned my Ph.D. in Mechanical Engineering from the University of Connecticut in December 2024, where my dissertation focused on reinforcement learning-guided multi-objective optimization for inverse analysis in complex engineering systems.

My research addresses a fundamental challenge in modern engineering: how to achieve accurate and reliable diagnostics under inherent information scarcity. I develop computational frameworks that bridge physics-based modeling, data-driven intelligence, and sparse sensing to enable trustworthy decision-making in resource-constrained environments. My work spans inverse problems and optimization, sparse representation and compressive sensing, and knowledge-enhanced AI for zero-shot generalization, with applications in structural health monitoring, prognostics and health management, and intelligent manufacturing.

At the core of my research is the conviction that engineering intelligence must be both physically grounded and computationally efficient—capable of delivering not only accurate predictions but also reliable, explainable insights that engineers can trust in safety-critical applications.