Associate Professor Yongxin Chen has been awarded the Manfred Thoma Medal from the International Federation of Automatic Control (IFAC) for his work in stochastic control, becoming the first honoree from Georgia Tech.

“Receiving this award means a lot to me. It’s a significant recognition from the community, and it motivates me to continue what I’ve been doing and keep advancing the frontier of stochastic control and related areas,” said Chen.

The medal was established in 2015 and recognizes outstanding contributions in the broad field of systems and control by a young researcher or engineer under the age of 40.

Chen will receive his medal in August at the 23^rd IFAC World Congress in Busan, Korea.

"We are tremendously proud to see Chen recognized. This award reflects not only the depth and originality of his contributions to stochastic control, but also his growing impact on the global control community,” said Mitchell Walker, AE School chair. “His work exemplifies the innovative, high‑caliber research that defines the AE School. His achievements continue to elevate Georgia Tech’s leadership in the field, and we look forward to the findings his scholarship will inspire in the years ahead."

Chen started working in controls while earning his Ph.D. at the University of Minnesota. His work focuses on one of its key branches: stochastic control, which centers on decision‑making under uncertainty. Early in his career, he became interested in the connection between stochastic control and optimal transport -- then largely independent areas. By bringing these fields together, he developed a new direction within stochastic control that is now widely used.

For example, during drone light shows each drone is equipped with LED lights and together they form large 3D shapes. Each drone is an individual object with its own motors, sensors and GPS position, but the objective is a cohesive formation from the swarm of drones

From a mathematical standpoint, each formation is a distribution of drones in 3D space. Chen’s method, treats the drone swarm as a single evolving distribution instead of planning a path for each drone individually, which would be really complex,. His algorithm computes the most efficient way to steer the distribution from one shape to another while considering uncertainty, such as wind, GPS noise, or slight variations in drone performance.

Chen is currently exploring the intersection of stochastic control and generative AI. He sees significant potential for control-theoretic techniques to enhance AI and machine learning systems, particularly through scalable computational methods. One algorithm developed by his group is already being used for text‑to‑image and text-to-video generation and is available through open‑source packages.

Looking ahead, Chen believes that many modern AI challenges can be reframed and solved using the mathematical tools of stochastic control. He will continue to explore the ways his research can be used across disciplines.