Interactive Machine Learning Lab

Our lab, led by Prof. Kwang-Sung Jun, studies a broad range of problems in interactive machine learning (IML). Our research spans reinforcement learning, bandit algorithms, Bayesian optimization, and active learning, as well as emerging problems in LLM post-training, alignment, and test-time scaling.

We develop efficient algorithms with rigorous mathematical guarantees, study the theoretical properties of widely used methods, and empirically investigate practical algorithms for modern machine learning systems. We collaborate closely with Krafton AI on LLM post-training and with Meta Platforms on efficient experimentation and A/B testing. Please visit our research page to learn more.

We are actively recruiting self-motivated students for MS and PhD programs, as well as undergraduate interns (preferably onsite). Visit the members page to meet the lab, and see our research and publications pages for our recent work. If you are interested in joining us, please email the PI!