Scholar

Minsu Kim

Google Scholar ID: VvyLuhAAAAAJ

Postdoctoral Researcher at Mila / KAIST

Generative ModelsCombinatorial OptimizationDeep LearningReinforcement Learning

Citations & Impact

All-time

Citations

1,060

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

20 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Academic Achievements

- 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)
- DesignCon 2021 Best Paper Award (as a First author)
- IEEE EDAPS 2020 Best Student Paper Award (as a Second author)

Research Experience

- CIFAR AI Safety Post-doc Fellow, Mila & KAIST, collaborating with Prof. Yoshua Bengio, Prof. Sungjin Ahn, and Prof. Sungsoo Ahn
- Worked with Prof. Sungsoo Ahn and his student Hyosoon Jang on generative models for scientific discovery
- Collaborated with Prof. Yoshua Bengio's group at Mila from December 2023 to May 2024 on GFlowNets
- During his master’s degree, under the supervision of Prof. Joungho Kim, focused on signal integrity and power integrity in 2.5D/3D semiconductor architectures, developing advanced deep learning algorithms for automating and optimizing hardware layout design and device placement

Education

Background

CIFAR AI Safety Post-doc Fellow, currently working at Mila and KAIST. Research interests include 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. Additionally, he enjoys interdisciplinary collaborations with experts in industrial engineering, hardware engineering, and drug discovery.

Miscellany

Personal interests include interdisciplinary collaborations, particularly in the fields of 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).

Co-authors

24 total