Seunghyeok Shin

I am an M.S.–Ph.D. student in the Department of Electrical and Computer Engineering at Inha University, where I am a member of the Machine Intelligence Lab advised by Prof. Hongki Lim. My research lies at the intersection of diffusion models, inverse problems, and 3D reconstruction.

I am particularly interested in developing methods that can model and leverage conditional distributions more faithfully. More broadly, my research seeks to develop methods for representing and learning conditional distributions across diverse settings, including inverse problems and multimodal learning. I am particularly interested in how generative models can capture complex dependencies between different forms of information and enable reliable conditional generation and inference.

My work has appeared at NeurIPS 2025 (Spotlight), ICLR 2026, and ICML 2026. I also serve as a reviewer for NeurIPS 2026.