Minbeom Kim
Hi! I am a final year Ph.D candidate at Seoul National University advised by Prof. Kyomin Jung and a student researcher at Google. I also have also interned at LawZero and NAVER Labs Europe .
My research centers on Safe and Controllable Agentic AI systems:
-
RL & its variant algorithms — Distributional Matching RL for RLHF (CriticControl, AdvisorQA, Drift) and RLVR (GUARD, PACED-RL),
-
Construction of safety guardrails (LifeTox, CausalArmor) and benchmarks (AdvisorQA, VLind-Bench),
-
And its applications to AI agents (ReflAct, Syntra, CausalArmor) and practical deployments (SumGD, CCI, Drift, ReflectCAP).
In particular, I’m interested in how to prevent harm from misalignment in future, more capable AI Agents.
Please feel free to reach out to me for a discussion here minbeomkim@snu.ac.kr!
📍 I am currently seeking Research Scientist positions (or equivalent roles) starting in mid-2026.
news
| May 01, 2026 | Our 🛡️ CausalArmor and 🕹️ PACED-RL are accepted to ICML 2026! See you in Seoul. 🇰🇷 |
|---|---|
| Oct 02, 2025 | I have joined Google as a Student Researcher. |
| Sep 18, 2025 | Our Syntra is accepted to NeurIPS 2025!!! See you in San Diego, USA. 🇺🇸 |
| Aug 20, 2025 | Our 🏎️ Drift and 🤖 ReflAct are accepted to EMNLP 2025!!! See you in China. 🇨🇳 |
| Jun 01, 2025 | I have joined 🧪LawZero founded by Yoshua Bengio as a research intern!! I will contribute to the Scientist AI project. Watch this wonderful journey [🍿TED Link]! |
| Jan 23, 2025 | Our 🛡️GUARD is accepted to ICLR 2025!! See you in Singapore. 🇸🇬 |
| Jan 22, 2025 | Our 3 papers are accepted to NAACL 2025!!! See you in Albuquerque, USA. 🇺🇸 |
| Oct 10, 2024 | After an amazing internship at Naver Labs Europe, our new paper Guaranteed Generation is out!! 💯 |
