Hello, I'm Dongseok Kim. I work on Artificial Intelligence and Machine Learning, with a focus on developing general-purpose methods and frameworks that are theoretically grounded, practically meaningful, and broadly applicable across domains.

My research interests include eXplainable AI (XAI), Uncertainty Quantification (UQ), ML Fairness, AI Governance, and AI Ethics. I am especially interested in how these areas can be connected to build AI systems that are not only accurate, but also interpretable, reliable, fair, and accountable in real-world decision-making contexts.

I see trustworthy AI as an interdisciplinary challenge. Rather than treating technical performance, uncertainty, fairness, ethics, and governance as separate issues, I aim to study how they interact with one another and how they can be integrated into coherent methods for responsible AI and ML.

I value research that connects ideas across Mathematics, Statistics, Computer Science, and the broader social and institutional contexts in which AI systems are deployed. By approaching problems from multiple perspectives—formal theory, empirical evaluation, practical constraints, and normative reasoning—I hope to develop insights that are both rigorous and useful.

My goal is not to be confined to a single application domain or narrow subfield. I aim to contribute to the advancement of AI and ML themselves by developing ideas, methods, and frameworks that can support more trustworthy, transparent, and responsible intelligent systems across a wide range of settings.