Hyunseung (Daniel) Hwang

PhD Candidate

Hyunseung (Daniel) Hwang is a PhD candidate in Electrical Engineering at KAIST, specializing in machine learning interpretability and explainability. His research critically investigates explanation techniques that are often taken for granted, exposing their limitations and proposing more robust, transparent alternatives. His major work, XClusters: Explainability-First Clustering, introduces a novel framework that prioritizes interpretability in undersupervised learning by generating time series cluster explanations grounded in domain knowledge and feature attributions. He also studies how tools like SHAP can be subtly manipulated, with implications for fairness and trust in AI systems.

Explainability of AI applications is crucial in decision-making processes where the risk of incorrect predictions influences individuals, groups, and governments. He seeks to build robust explanations that can lead to decisions with high confidence to prevent such risks.