Minsu Kim

I’m a Ph.D. Candidate in the Industrial and Systems Engineering department at KAIST, where I am advised by Prof. Jinkyoo Park. I also closely collaborate with Prof. Sungsoo Ahn.

I’m visiting Prof. Yoshua Bengio’s group at the Mila - Quebec AI Institute from 2023/11 to 2024/09 for collaborating GFlowNets research.

I’m eager to study and investigate deep learning and machine learning methods (e.g., deep reinforcement learning, generative modelling, amortized inference) for exploring discrete, combinatorial, structured space.

I’m interested in following topics of new learning algorithms:

• GFlowNets (e.g., better exploration and credit assignments for GFlowNets)
• Diffusion Models (e.g., discrete diffusion and diffusion-based GFlowNets)
• Learning-based Meta Heuristics (e.g., neural evolutionary algorithms, and local search)
• Deep Reinforcement Learning (e.g., replay training for sample efficient DRL)

My research applications includes:

• Drug discovery (e.g., de novo discovery of small molecular graphs)
• Computational biology (e.g., DNA, RNA, and 3D Antibody design)
• Finetuning Large Multimodal Model (Finetuning Text-to-Image Model with Human Feedback)
• Safety alignment of large language model (e.g., Probabilistic Red-Teaming)
• Hardware design optimization (e.g., Placement of decoupling capacitance, and channel routing)
• Combinatorial optimization (e.g., Vehicle routing, scheduling, and graph covering).

Education

• Ph.D. Candidate at KAIST IE
  • Advisor: Prof. Jinkyoo Park
  • 2022.Mar ~ 2025.Feb (Expected)
• 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

• 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

• Conference Reviewer: NeurIPS, ICML, ICLR, AISTATS, IJCAI, Learning on Graphs (LoG)
• Journal Reviewer: IEEE Transactions on Neural Networks and Learning Systems (TNNLS)