Lecturer at the Gaoling School of Artificial Intelligence, Renmin University of China. He received his Ph.D. from the Swiss Federal Institute of Technology Lausanne (EPFL) in 2026 and was a visiting scholar at the University of California, Los Angeles (UCLA). His main research interests are machine learning theory and optimization, with a particular focus on studying the training dynamics of neural networks from an optimization-theoretic perspective. He also applies optimization methods to research on trustworthy large language models. He has published more than 10 papers in major artificial intelligence conferences and journals, including NeurIPS, ICML, ICLR, and IEEE TPAMI. He organized a workshop on pitfalls in large-model fine-tuning at the EPFL Center for Digital Trust and assisted in organizing the NeurIPS 2024 FITML Workshop. He received an annual scholarship from KTH Royal Institute of Technology. He has regularly served as a reviewer for international conferences and journals including NeurIPS, ICLR, ICML, AISTATS, IJCV, and TMLR.