Study Interests

• [Generative Artificial Intelligence] Exploring the theoretical principles and algorithmic implementations of probabilistic and transport-based generative models across continuous, discrete, Hilbert state spaces.
• [Artificial Intelligence for Science] Applying machine learning techniques to solve complex scientific problems, particularly in molecular generation, molecular interaction modeling, and protein science, with applications in drug discovery.
• [Mathematical Foundations] Studying mathematical foundations of learning systems, including symmetry (equivariance, group and representation theory), approximation (UATs), dynamical systems theory, and transport theory.
• [Human Intelligence] Exploring intelligence systems from multiple persepctives including neuroscience and chaos theory (the brain as a complex system), information theory (uncertainty and entropy), psychology (psychological entropy), sociology, philosophy, and religion (The Denial of Death).