Minbeom Kim

Hi! I am a Ph.D student at Seoul National University. I am fortunate to be advised by Prof. Kyomin Jung. Previously, I received B.E. degree from KAIST. I have also interned at NAVER AI LAB and NAVER Labs Europe for controlled text generation.
My Ph.D. research primarily focuses on Controlled Generation from Large Language Models. More specifically, how can we control generations that are 1) guaranteed to strictly satisfy essential constraints (e.g. safety guarantee), 2) aligned with personal preferences, and 3) still preserving pre-aligned general preferences? As a practical and impactful solution for challenges, I strongly believe that harmony between training-time methods and inference-time methods is essential. Although it looks deeply challenging, I am enjoying this journey and looking forward to the new insights it will bring. ๐
news
Sep 18, 2025 | Our Syntra is accepted to NeurIPS 2025!!! See you in San Diego, USA. ๐บ๐ธ |
---|---|
Aug 20, 2025 | Our ๐๏ธ Drift and ๐ค ReflAct are accepted to EMNLP 2025!!! See you in China. ๐จ๐ณ |
Jun 01, 2025 | I have joined ๐งชLawZero founded by Yoshua Bengio as a research intern!! I will contribute to the Scientist AI project. Watch this wonderful journey [๐ฟTED Link]! |
Jan 23, 2025 | Our ๐ก๏ธGUARD is accepted to ICLR 2025!! See you in Singapore. ๐ธ๐ฌ |
Jan 22, 2025 | Our 3 papers are accepted to NAACL 2025!!! See you in Albuquerque, USA. ๐บ๐ธ |
Oct 10, 2024 | After an amazing internship at Naver Labs Europe, our new paper Guaranteed Generation is out!! ๐ฏ |
Jul 15, 2024 | Our new paper VLind-Bench is out!!๐ We also release code and dataset!. |
Mar 14, 2024 | LifeTox was accepted at NAACL 2024 as Oral Presentation. See you in Mexico! ๐ฎ |