Research
Our research focuses on developing and applying machine learning methods to solve challenging problems in computational chemistry and materials science.
Machine Learning Potentials
Transferable neural network potentials bridging quantum accuracy with computational efficiency for molecular simulations
Learn more →
AI for Drug Discovery
Energy-driven, decision-oriented computational methods integrating machine learning for pharmaceutical applications
Learn more →
Generative AI in Chemistry
Generative models enabling systematic exploration of chemical space under biological and synthetic constraints
Learn more →
Experiment Automation
ML-enabled workflows for scalable, reliable, and reproducible chemical experimentation in cloud laboratories
Learn more →
Quantum Chemistry
First-principles electronic structure methods providing the theoretical foundation for ML potential development
Learn more →
Materials Informatics
Machine learning-accelerated discovery and optimization of advanced functional materials
Learn more →
Reactions & Reactivity
ML-accelerated reaction modeling enabling exploration of chemical transformations at unprecedented scale
Learn more →
Our Approach
We believe in combining rigorous theoretical foundations with practical applications. Our work bridges the gap between fundamental science and real-world impact, always with an eye toward reproducibility and open science.