Minsu Kim
I am an incoming Senior Researcher at Microsoft Frontier Tuning, where I will work on reinforcement learning (RL) for LLM agents. Before that, I was a postdoctoral fellow working with Prof. Yoshua Bengio at Mila, and Prof. Sungjin Ahn and Prof. Sungsoo Ahn at KAIST.
I received my Ph.D. from KAIST in Prof. Jinkyoo Park’s group, working on RL for combinatorial optimization. Previously, I received my M.S. from KAIST in Prof. Joungho Kim’s group, working on learning-based hardware design optimization. I obtained my B.S. in Mathematics and Computer Science from KAIST.
Research Interests
- Combinatorial optimization: NP-hard problems and black-box optimization
- Reinforcement learning: long-horizon credit assignment and sample-efficient exploration
- AI4Science: molecular sampling/optimization and biological sequence design
Academic Service
- Area Chair: NeurIPS (Position Paper Track, 2026)
- Reviewer (Conferences): NeurIPS (2022–2025), ICML (2023–2026), ICLR (2024–2026)
- Reviewer (Journals): TNNLS (2025–2026), TPAMI (2025), TMLR (2025)
News
| May 02, 2026 | 2 papers (Active Attacks and S3GFN) are accepted at ICML 2026! |
|---|---|
| Feb 09, 2026 | 2 papers (LVI and DAV) are accepted at ICLR 2026! |
| Sep 26, 2025 | 4 papers (SGDS, TBA, EGM, and ABCD) are accepted at NeurIPS 2025! |
| May 02, 2025 | 2 papers (Delta-CS and ODS) are accepted at ICML 2025! |
| Apr 02, 2025 | I’ve selected Jang Yeong SIL Fellowship Award. |