By combining machine learning (ML) with density functional theory (DFT), we accelerate materials discovery through rapid screening and property prediction. Using generative AI, we aim to design novel materials with enhanced stability and functionality.

By employing machine learning potentials (MLPs), we can perform large-scale and long-time simulations that are impossible with traditional DFT, while maintaining near-DFT accuracy. This approach enables efficient and realistic multiscale simulations, allowing us to analyze material behaviors more closely to experiment.

By employing first-principles calculations such as Density Functional Theory (DFT) and Ab Initio Molecular Dynamics (AIMD), we focus on elucidating catalytic reaction mechanisms at the atomic level to accelerate the design of novel materials with enhanced efficiency and stability.

Leveraging advanced ab-initio calculations and large-scale simulations, we aim to reveal the microscopic dynamic processes of battery systems by focusing on bulk electrolytes and reactions at the electrode-electrolyte interface.