Yuxuan Xia is a Visiting Student at the Mens, Manus and Machina (M3S) group at SMART, where he works on resource-efficient vision-language-action (VLA) models for robotics, with a focus on the trade-off between efficiency and reliability in closed-loop control. 

He is currently pursuing an MSc in Computer Control and Automation at Nanyang Technological University, where his dissertation develops convergence-guaranteed incremental learning methods for robot vision. He received his B.Eng. in Communication Engineering from Guangzhou University. His research interests include robot learning, efficient inference, and reliable autonomous systems.