Minseong Bae

I am a M.S. student at KAIST MLV Lab (School of Computing), advised by Prof. Hyunwoo J. Kim. Previously, I received my B.E. in Computer Science and Engineering and Mathematics from Korea University in 2025. For more details, please see my CV.

My research interests lie in generative modeling across diverse modalities and geometric deep learning, particularly in their applications to the natural sciences for tackling impactful real-world problems (AI4Science).

Recently, I have been particularly interested in generative model-based world modeling, reward-guided generation, and agentic systems for scientific modeling and discovery. Through these directions, I aim to develop methods that integrate reasoning, generative modeling, and representation learning to model, simulate, and optimize complex scientific phenomena.

My long-term research goal is to build robust and scalable learning frameworks that support the scientific research loop and enable self-improving, human-collaborative agents for scientific discovery.

Feel free to reach out via email if you’d like to discuss anything related to me!