About me

Welcome! I am a machine learning researcher and an Assistant Professor in Data Science at The University of Memphis. Previously, I obtained my PhD in Computing and Information Sciences at Rochester Institute of Technology, working in the Machine Learning and Data Intensive Computing Lab under Dr. Qi Yu.

My research centers on active learning, uncertainty-aware machine learning, and adaptive experimental design, with applications spanning scientific discovery, AI robustness, and real-world decision-making. I aim to develop efficient, principled, and responsible learning algorithms that can make the most of limited supervision and adapt to challenging scenarios such as noisy labels, limited validation budgets, and domain shifts. I am also closely collaborating with the High-Energy-Density Physics (HEDP) Theory Group from University of Rochester. My works have been published or is forthcoming in NeurIPS, AAAI, ICML, IOP:MLST, among other outlets. In these research projects, I try to solve challenging issues of multi-label active learning, noisy-label active learning, active testing-while-learning, active test-time adaptation of large pre-trained foundation models, and data-efficient physics-informed machine learning models. While primarily focused on machine learning novel algorithm development, I am enthusiastic about applying active learning and other learning techniques to real-world problems in Computer Vision, Natural Language Processing, Scientific Experimental Design, Medical Research, Augmented & Virtual Reality, etc.

I am looking for motivated PhD students to join my research group at The University of Memphis. Our group focuses on advancing fundamental and applied research in machine learning, with particular interest in Active Learning, Uncertainty Quantification, and AI for Science. Students will have the opportunity to work on cutting-edge research problems, publish in top-tier venues (NeurIPS, ICML, AAAI, etc.), and collaborate across disciplines.