Research Areas

Scientific Machine Learning

We develop advanced scientific machine learning algorithms tailored for predicting material behaviors and properties, catering to a wide range of engineering applications.

Reliability for Semiconductors

We utilize cutting-edge computational simulations and machine learning techniques to model failure mechanisms in semiconductors, aiming to significantly improve the reliability predictions and performance of microelectronic devices.

Physical Intelligence and Robotics

This project develops advanced Vision-Language-Action (VLA) models for physical intelligence on the Mobile ALOHA platform. By integrating multimodal perception, language understanding, and adaptive control, we aim to enable autonomous and intelligent real-world task execution.

Advanced Energy Materials

Our research employs advanced computational techniques to design state-of-the-art materials and structures for diverse energy applications, including nuclear energy and Li-ion batteries.

Interfaces in Materials

We explore the impact of various interfaces on material properties to uncover fundamental mechanisms, empowering us to design advanced materials through strategic interfacial engineering.