My research interests are in the intersection of machine learning and control theory, spanning the entire spectrum from theory and foundations, and practical algorithms, to real-world applications in robotics and autonomy. To that end, there are three goals: (1) bridge learning and control theory in a unified framework; (2) design reliable learning and control algorithms with formal guarantees such as safety, stability, and robustness; and (3) push the boundaries of agile robotic control with new capabilities (see a few examples in my homepage). My research has been published in prestigious journals (e.g., Science Robotics, IEEE T-RO, ACM SIGMETRICS) and conferences (e.g., NeurIPS, ICRA, ACC, L4DC) and covered by the press (e.g., CNN, Reuters, Yahoo!, Meta, Caltech front page).
I received a Ph.D. from Caltech in 2022 and a B.E. from Tsinghua University in 2017. I was also an ML research intern at NVIDIA in 2020. I was awarded the Simoudis Discovery Prize and the Ben P.C. Chou Doctoral Prize at Caltech and was named a Rising Star in Data Science by the University of Chicago.