The Causal Artificial Intelligence Lab (CAIL) pursues three major research directions to advance causal inference and artificial intelligence. Our work bridges theory, methodology, and applications, aiming to produce explainable, equitable, and impactful AI systems.
Causal Discovery & Inference
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Praesent eget suscipit ipsum, nec rhoncus nisl. Curabitur feugiat nulla nec ante vulputate, at cursus leo suscipit. We develop scalable, knowledge-guided methods for identifying cause–effect relationships from observational and time-series data. Donec posuere bibendum dui, ut congue leo sodales ac. Proin interdum luctus fermentum. Learn moreCausal Representation Learning
Lorem ipsum dolor sit amet, consectetur adipiscing elit. In vel lacus vitae est tristique luctus. Mauris tristique purus vel nisi viverra, nec ullamcorper lacus elementum. We focus on representation learning approaches that incorporate causal structures to improve robustness, generalization, and fairness in machine learning systems. Aliquam erat volutpat. Etiam at turpis sit amet lectus viverra accumsan. Learn more
Applications in Climate & Health
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed vel mi vel lectus imperdiet luctus at nec massa. Our research applies causal inference and AI to climate science, public health, and mobility systems. We aim to provide actionable insights and decision-support tools that areexplainable and trustworthy. Integer at magna vel dui scelerisque tincidunt. Learn more