Minsu Kim

I am a CIFAR AI Safety Post-doc Fellow, currently working with Prof. Yoshua Bengio at Mila, and Prof. Sungjin Ahn and Prof. Sungsoo Ahn at KAIST. I am also serving as an Academic Collaborator of LawZero, a non-profit organization focused on safe AI.

I work on fundamental challenges in machine learning, including exploration in reinforcement learning, credit assignment in long-horizon decision making, amortized sampling & variational inference, and uncertainty quantification, with a focus on their applications to LLM/LMM training and inference.

Beyond core ML research, I enjoy interdisciplinary collaborations with domain experts across diverse fields, including industrial engineering (e.g., smart factories, transportation), hardware engineering (e.g., signal and power integrity), and drug discovery (e.g., small-molecule generation and molecular dynamics).

Backgrounds

I got a Ph.D. at KAIST, under the guidance of Prof. Jinkyoo Park.

During my Ph.D., I’ve had the privilege of collaborating with several professors and their research groups:

• I have been working with Prof. Sungsoo Ahn on generative models for scientific discovery, including our joint efforts on GFlowNets with his student, Hyosoon Jang.

• I have also engaged deeply with researchers at Mila, having physically visited Prof. Yoshua Bengio’s group from December 2023 to May 2024. Throughout this period, I’ve been fortunate to collaborate with many talented researchers for GFlowNets, including Emmanuel Bengio, Nikolay Malkin, Seanie Lee, Moksh Jain, Siddarth Venkatraman, and Dinghuai Zhang, among others.

Before pursuing my Ph.D., I completed my master’s degree under the supervision of Prof. Joungho Kim, an expert in designing 3D ICs (e.g., HBM) for SI/PI performance.

My research at master prieods.

One surprising fact about my background is that I worked in hardware system design and analysis from 2020 to 2022 during my master’s degree. My focus was on signal integrity and power integrity in 2.5D/3D semiconductor architectures, including high-bandwidth memory (HBM) modules. I developed advanced deep learning algorithms to automate and optimize hardware layout design and device placement. These experiences provided me with a deep understanding of computing systems and HBM, which are crucial for AI computing, as well as practical knowledge in using deep learning methods for hardware optimization challenges.

Education

• Ph.D. at KAIST IE
  • Advisor: Prof. Jinkyoo Park
  • 2022.Mar ~ 2025.Feb
• M.S. at KAIST EE
  • Advisor: Prof. Joungho Kim
  • 2020.Mar ~ 2022.Feb
• B.S. at KAIST, Math and CS (Dual Degree)
  • 2015.Mar ~ 2020.Feb

Awards

• Jang Yeong Sil Fellowship (2025)
• KAIST Presidential Best Ph.D. Thesis Award
• Google Conference Scholarship for ICLR 2024 (as a First author of the paper “Local Search GFlowNets”)
• Qualcomm Innovation Fellowship Award 2023 Korea (as a First author of the paper “Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimization”)
• NeurIPS 2022 Scholar Award (Travel Grant)
• DesignCon 2022 Best Paper Award (as a Second author for a paper of Haeyeon Rachel Kim)
• DesignCon 2022 Best Paper Award (as a Second author for a paper of Seonguk Choi)
• DesignCon 2021 Best Paper Award (as a First author)
• IEEE EDAPS 2020 Best Student Paper Award (as a Second author for a paper of Kyungjune Son)

Academic activities

• Reviewer (Conference): NeurIPS, ICML, ICLR, AISTATS, AAAI, IJCAI, Learning on Graphs (LoG)
• Reviewer (Journal): IEEE Transactions on Neural Networks and Learning Systems (TNNLS), IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Transactions on Machine Learning Research (TMLR)
• Senior Reviewer: Reinforcement Learning Conference (RLC)