Interactive Machine Learning Lab
Our lab, led by Prof. Kwang-Sung (Kwang) Jun (GSAI/CSE @ POSTECH), studies a broad range of problems in interactive machine learning (IML).
We develop efficient algorithms with rigorous mathematical guarantees, study the theoretical guarantees of widely used methods, and empirically investigate practical algorithms for modern machine learning systems. We collaborate closely with Krafton AI on LLM post-training/reasoning/test-time scaling and with Meta Platforms on efficient experimentation and A/B testing. Please visit our research page to learn more.
We are actively recruiting – see hiring.
news
| Oct 13, 2026 | 3 NeurIPS papers! Online RLHF with general preference model, fixed budget Monte Carlo tree search, and LLM fine tuning with GRPO with clipping replaced by signed logarithmic smoothing! |
|---|---|
| Oct 07, 2026 | We successfully co-organized the LeT workshop @ POSTECH! This workshop brought together learning theory researchers from across Korea for networking and discussion. |
| Sep 02, 2026 | The lab page has been renewed! |
| Jul 01, 2026 | Apr’26-Jul’26: 1 AISTATS, 1 ICLR, 2 ICML, 1 COLT, 1 TMLR |
| Jan 01, 2026 | Our lab has moved to POSTECH. It is one of the top research universities in South Korea! We are actively recruiting! |