author
Jingwu Tang
Focused on decision-making and trustworthy AI, this Carnegie Mellon researcher works at the intersection of reinforcement learning, imitation learning, privacy, and calibration. His work explores how machine learning systems can make better decisions in complex real-world settings.
0 Audiobooks
About the author
A PhD student in the School of Computer Science at Carnegie Mellon University, he is advised by Steven Wu and Fei Fang. Before moving to Carnegie Mellon, he studied in the Turing Class at Peking University and worked with Xiaotie Deng.
His research centers on reinforcement learning, imitation learning, and multi-calibration, with more recent interest in the theoretical side of post-training for large language models. His publications include work presented at major machine learning venues such as ICML, NeurIPS, and ICLR, covering topics like auction design, private synthetic data, and decision calibration.
Alongside research, he has also contributed as a teaching assistant and reviewer for leading AI conferences and workshops. His profile suggests a scholar interested not only in technical theory, but also in how intelligent systems behave in practice and how their decisions can be made more reliable.