Flexible Machine Learning
fast, memory-efficient, and deployable

We develop and analyze fast and memory-efficient machine learning algorithms — inspired by theoretical background— for efficient deployment of Artificial Intelligence models.

Recruitment

FlexML is currently recruiting self-motivated incoming graduate students with strong backgrounds in mathematics, computer science, or electrical engineering starting from Fall 2026. We are looking for individuals passionate about developing efficient ML/AI algorithms, with a strong theoretical foundation and practical impact. Postdoctoral and visiting researcher positions are also available. If you are interested in joining our team, please email me with your CV, transcript, and a brief statement of research interests (insu.han@kaist.ac.kr).

News & Highlights

Mar 2026
Join
Jihwan Shin joined the FlexML group. Welcome!
Jan 2026
Paper
PolarQuant: Quantizing KV Caches with Polar Transformation
Accepted at AISTATS 2026
Sep 2025
Join
Seongjin Cha and Langqing Cui joined the FlexML group. Welcome!