Statistical Artificial Intelligence Lab · KAIST
We study how machines learn, infer, and make decisions in complex systems—then bring those ideas into weather, science, robotics, language, and industry.
Current researchGranular Concept CircuitsDahee Kwon, Sehyun Lee, and Jaesik ChoiAreas of inquiry
From the lab
Haksoo Lim, Myeongjin Lee, Wonjoon Chang, and Jaesik Choi Unified Backbone Refinement for Diffusion Models via Internal-Latent Analysis European Conference on Computer Vision (ECCV) 2026.
Read the announcementA lab for consequential questions
“How can an intelligent system remain useful when the data are uncertain, the environment changes, and people need to understand the decision?”
SAIL connects statistical inference with modern machine learning. Our work moves between theory and deployment, shaped by the demands of real systems.
About SAILWorking together
28 partners across industry, national institutes, and universities
