publications

(*) is used to denote equal contribution.

2024

  1. arXiv
    Adaptive Teachers for Amortized Samplers
    Minsu Kim*, Sanghyeok Choi*, Taeyoung Yun, Emmanuel Bengio, Leo Feng, Jarrid Rector-Brooks, Sungsoo Ahn, Jinkyoo Park, Nikolay Malkin, and Yoshua Bengio
    arXiv preprint arXiv:2410.01432 2024
  2. arXiv
    Ant Colony Sampling with GFlowNets for Combinatorial Optimization
    Minsu Kim*, Sanghyeok Choi*, Jiwoo Son, Hyeonah Kim, Jinkyoo Park, and Yoshua Bengio
    arXiv preprint arXiv:2403.07041 2024
  3. arXiv
    Decoupled Sequence and Structure Generation for Realistic Antibody Design
    Nayoung Kim, Minsu Kim, Sungsoo Ahn, and Jinkyoo Park
    arXiv preprint arXiv:2402.05982 2024
  4. NeurIPS WS
    Generative Flows on Synthetic Pathway for Drug Design
    Seonghwan Seo, Minsu Kim, Tony Shen, Martin Ester, Jinkyoo Park, Sungsoo Ahn, and Woo Youn Kim
    NeurIPS Workshop on AI for New Drug Modalities 2024
  5. NeurIPS WS
    Improved Off-policy Reinforcement Learning in Biological Sequence Design
    Hyeonah Kim, Minsu Kim, Taeyoung Yun, Sanghyeok Choi, Emmanuel Bengio, Alex Hernández-Garcı́a, and Jinkyoo Park
    NeurIPS Workshop on AI for New Drug Modalities 2024
  6. NeurIPS WS
    MOFFlow: Flow Matching for Structure Prediction of Metal-Organic Frameworks
    Nayoung Kim, Seongsu Kim, Minsu Kim, Jinkyoo Park, and Sungsoo Ahn
    NeurIPS Workshop on AI for New Drug Modalities 2024
  7. NeurIPS WS
    Chiplet Placement and Routing Optimization: A Novel Benchmark and Neural Solver
    Haeyeon Kim, Federico Berto, Chuanbo Hua, Minsu Kim, Joungho Kim, and Jinkyoo Park
    NeurIPS Workshop on Machine Learning for Systems 2024
  8. NeurIPS WS
    Learning Diverse Attacks on Large Language Models for Robust Red-teaming and Safety Tuning
    Seanie Lee, Minsu Kim, Lynn Cherif, David Dobre, Juho Lee, Sung Ju Hwang, Kenji Kawaguchi, Gauthier Gidel, Yoshua Bengio, Nikolay Malkin, and Moksh Jain
    NeurIPS Workshop on Red Teaming GenAI 2024
  9. NeurIPS WS Oral
    Amortizing Intractable Inference in Diffusion Models for Bayesian Inverse Problems
    Siddarth Venkatraman*, Moksh Jain*, Luca Scimeca*, Minsu Kim*, Marcin Sendera*, Mohsin Hasan, Luke Rowe, Sarthak Mittal, Pablo Lemos, Emmanuel Bengio, Alexandre Adam, Jarrid Rector-Brooks, Yashar Hezaveh, Laurence Perreault-Levasseur, Yoshua Bengio, and 2 more authors
    NeurIPS Workshop on Machine Learning and the Physical Sciences (this is partial extended version of the NeurIPS 2024 Paper) 2024
  10. NeurIPS
    Amortizing Intractable Inference in Diffusion Models for Vision, Language, and Control
    Siddarth Venkatraman*, Moksh Jain*, Luca Scimeca*, Minsu Kim*, Marcin Sendera*, Mohsin Hasan, Luke Rowe, Sarthak Mittal, Pablo Lemos, Emmanuel Bengio, Alexandre Adam, Jarrid Rector-Brooks, Yoshua Bengio, Glen Berseth, and Nikolay Malkin
    Advances in Neural Information Processing Systems 2024
  11. NeurIPS
    Pessimistic Backward Policy for GFlowNets
    Hyosoon Jang, Yunhui Jang, Minsu Kim, Jinkyoo Park, and Sungsoo Ahn
    Advances in Neural Information Processing Systems 2024
  12. NeurIPS
    Improved Off-policy Training of Diffusion Samplers
    Marcin Sendera, Minsu Kim, Sarthak Mittal, Pablo Lemos, Luca Scimeca, Jarrid Rector-Brooks, Alexandre Adam, Yoshua Bengio, and Nikolay Malkin
    Advances in Neural Information Processing Systems 2024
  13. NeurIPS
    Genetic-guided GFlowNets for Sample Efficient Molecular Optimization
    Hyeonah Kim, Minsu Kim, Sanghyeok Choi, and Jinkyoo Park
    Advances in Neural Information Processing Systems 2024
  14. ICML
    Learning to Scale Logits for Temperature-Conditional GFlowNets
    Minsu Kim*, Joohwan Ko*, Taeyoung Yun*, Dinghuai Zhang, Ling Pan, Woochang Kim, Jinkyoo Park, Emmanuel Bengio, and Yoshua Bengio
    International Conference on Machine Learning 2024
  15. ICML
    Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization
    Hyeonah Kim, Minsu Kim, Sungsoo Ahn, and Jinkyoo Park
    International Conference on Machine Learning 2024
  16. AAAI
    Equity-Transformer: Solving NP-hard Min-max Routing Problems as Sequential Generation with Equity Context
    Jiwoo Son*, Minsu Kim*, Sanghyeok Choi, Hyeonah Kim, and Park Jinkyoo
    AAAI Conference on AI 2024
  17. ICLR Spotlight
    Local Search GFlowNets
    Minsu Kim, Taeyoung Yun, Emmanuel Bengio, Dinghuai Zhang, Yoshua Bengio, Sungsoo Ahn, and Jinkyoo Park
    International Conference on Learning Representations 2024
  18. ICLR Oral
    Learning Energy Decompositions for Partial Inference of GFlowNets
    Hyosoon Jang, Minsu Kim, and Sungsoo Ahn
    International Conference on Learning Representations 2024

2023

  1. NeurIPS WS Oral
    Rl4co: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark
    Federico Berto, Chuanbo Hua, Junyoung Park, Minsu Kim, Hyeonah Kim, Jiwoo Son, Haeyeon Kim, Joungho Kim, and Jinkyoo Park
    NeurIPS Workshop on New Frontiers in Graph Learning 2023
  2. Appl. Intell.
    Temporal enhanced inductive graph knowledge tracing
    Donghee Han, Daehee Kim, Minsu Kim, Keejun Han, and Mun Yong Yi
    Applied Intelligence 2023
  3. Bayesian Exploration Imitation Learning-Based Contextual via Design Optimization Method of PAM-4-Based High-Speed Serial Link
    Jihun Kim, Minsu Kim, Haeyeon Kim, Hyunwook Park, Seonguk Choi, Joonsang Park, Boogyo Sim, Keeyoung Son, Seongguk Kim, Jinwook Song, Youngwoo Kim, and Joungho Kim
    IEEE Transactions on Electromagnetic Compatibility 2023
  4. Deep Reinforcement Learning-based Optimal and Fast Hybrid Equalizer Design Method for High Bandwidth Memory (HBM) Module
    Seonguk Choi, Keeyoung Son, Hyunwook Park, Seongguk Kim, Boogyo Sim, Jihun Kim, Joonsang Park, Minsu Kim, Haeyeon Kim, Jinwook Song, Youngwoo Kim, and Joungho Kim
    IEEE Transactions on Components, Packaging and Manufacturing Technology 2023
  5. NeurIPS
    Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences
    Minsu Kim, Federico Berto, Sungsoo Ahn, and Jinkyoo Park
    Advances in Neural Information Processing Systems 2023
  6. ICML
    Meta-SAGE: A Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Large Scale Combinatorial Optimization
    Jiwoo Son*, Minsu Kim*, Hyeonah Kim, and Jinkyoo Park
    International Conference on Machine Learning 2023
  7. ICML
    DevFormer: A Symmetric Transformer for Context-Aware Device Placement
    Haeyeon Kim*, Minsu Kim*, Federico Berto, Joungho Kim, and Jinkyoo Park
    International Conference on Machine Learning 2023

2022

  1. NeurIPS Qualcomm innov.
    Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimization
    Minsu Kim, Junyoung Park, and Jinkyoo Park
    Advances in Neural Information Processing Systems (selected as Qualcomm Innovation Fellowship Award) 2022
  2. NeurIPS WS
    Neural Coarsening Process for Multi-level Graph Combinatorial Optimization
    Hyeonah Kim, Minsu Kim, Changhyun Kwon, and Jinkyoo Park
    In NeurIPS Workshop on New Frontiers in Graph Learning 2022
  3. Data-Efficient Machine Learning Method for Hardware Routing: Signal Integrity Demonstration to 2PDC and PCIe 6.0
    Minsu Kim, and  others
    In DesignCon 2022
  4. Transformer Network-based Reinforcement Learning Method for Power Distribution Network (PDN) Optimization of High Bandwidth Memory (HBM)
    Hyunwook Park, Minsu Kim, Seongguk Kim, Keunwoo Kim, Haeyeon Kim, Taein Shin, Keeyoung Son, Boogyo Sim, Subin Kim, Seungtaek Jeong, and  others
    IEEE Transactions on Microwave Theory and Techniques 2022
  5. Thermal and Signal Integrity Co-Design and Verification of Embedded Cooling Structure with Thermal Transmission Line (ECS-TTL) for High Bandwidth Memory Module
    Keeyoung Son, Seongguk Kim, Hyunwook Park, Taein Shin, Keunwoo Kim, Minsu Kim, Boogyo Sim, Subin Kim, Gapyeol Park, Shinyoung Park, and  others
    IEEE Transactions on Components, Packaging and Manufacturing Technology 2022

2021

  1. DesignCon Best paper
    Neural Language Model Enables Extremely Fast and Robust Routing on Interposer
    Minsu Kim, Hyunwook Park, Seonguk Choi, Haeyeon Rachel Kim, Seongguk Kim, Keeyoung Son, Keunwoo Kim, Daehwan Lho, Kyunjune Son, Subin Kim, and Joungho Kim
    In DesignCon 2021
  2. NeurIPS
    Learning collaborative policies to solve NP-hard routing problems
    Minsu Kim, Jinkyoo Park, and Joungho Kim
    Advances in Neural Information Processing Systems 2021
  3. Reinforcement-Learning-Based Signal Integrity Optimization and Analysis of a Scalable 3-D X-Point Array Structure
    Kyungjune Son, Minsu Kim, Hyunwook Park, Daehwan Lho, Keeyoung Son, Keunwoo Kim, Seongsoo Lee, Seungtaek Jeong, Shinyoung Park, Seokwoo Hong, and  others
    IEEE Transactions on Components, Packaging and Manufacturing Technology 2021
  4. Sequential Policy Network-based Optimal Passive Equalizer Design for an Arbitrary Channel of High Bandwidth Memory using Advantage Actor Critic
    Seonguk Choi, Minsu Kim, Hyunwook Park, Keeyoung Son, Seongguk Kim, Jihun Kim, Joonsang Park, Haeyeon Kim, Taein Shin, Keunwoo Kim, and Joungho Kim
    In 2021 IEEE 30th Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS) 2021
  5. Signal Integrity Analysis of High Speed Channel considering Thermal Distribution
    Keeyoung Son, Seongguk Kim, Minsu Kim, Daehwan Lho, Keunwoo Kim, Hyunwook Park, Gapyeol Park, and Joungho Kim
    In 2021 IEEE 30th Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS) 2021
  6. Deep Reinforcement Learning Framework for Optimal Decoupling Capacitor Placement on General PDN with an Arbitrary Probing Port
    Haeyeon Kim, Hyunwook Park, Minsu Kim, Seonguk Choi, Jihun Kim, Joonsang Park, Seongguk Kim, Subin Kim, and Joungho Kim
    In 2021 IEEE 30th Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS) 2021
  7. Crosstalk-included PAM-4 Worst Eye Diagram Estimation Method for High-speed Serial Links
    Hyunwook Park, Jihun Kim, Minsu Kim, Keunwoo Kim, Boogyo Sim, Daehwan Lho, Taein Shin, Keeyoung Son, Jinwook Song, Youngmin Ku, Jonggyu Park, and Joungho Kim
    In 2021 IEEE 30th Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS) 2021
  8. Deep Reinforcement Learning-based Pin Assignment Optimization of BGA Packages considering Signal Integrity with Graph Representation
    Joonsang Park, Minsu Kim, Seongguk Kim, Keeyoung Son, Taein Shin, Hyunwook Park, Jihun Kim, Seonguk Choi, Haeyeon Kim, Keunwoo Kim, and Joungho Kim
    In 2021 IEEE 30th Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS) 2021
  9. PAM-4 based PCIe 6.0 Channel Design Optimization Method using Bayesian Optimization
    Jihun Kim, Hyunwook Park, Minsu Kim, Seongguk Kim, Seonguk Choi, Keeyoung Son, Joonsang Park, Haeyeon Kim, Jinwook Song, Youngmin Ku, Jonggyu Park, and Joungho Kim
    In 2021 IEEE 30th Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS) 2021
  10. Imitation Learning for Simultaneous Escape Routing
    Minsu Kim, Hyunwook Park, Keeyoung Son, Seongguk Kim, Haeyeon Kim, Jihun Kim, Jinwook Song, Youngmin Ku, Jounggyu Park, and Joungho Kim
    In 2021 IEEE 30th Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS) 2021

2020

  1. Policy Gradient Reinforcement Learning-based Optimal Decoupling Capacitor Design Method for 2.5-D/3-D ICs using Transformer Network
    Hyunwook Park, Minsu Kim, Subin Kim, Seungtaek Jeong, Seongguk Kim, Hyungmin Kang, Keunwoo Kim, Keeyoung Son, Gapyeol Park, Kyungjune Son, Taein Shin, and Joungho Kim
    In 2020 IEEE Electrical Design of Advanced Packaging and Systems (EDAPS) 2020
  2. Design and Analysis of Thermal Transmission Line based Embedded Cooling Structures for High Bandwidth Memory Module and 2.5D/3D ICs
    Keeyoung Son, Subin Kim, Shinyoung Park, Hyunwook Park, Keunwoo Kim, Taein Shin, Minsu Kim, Kyungjune Son, Gapyeol Park, Seungtaek Jeong, and Joungho Kim
    In 2020 IEEE Electrical Design of Advanced Packaging and Systems (EDAPS) 2020
  3. Reinforcement Learning-based Auto-router considering Signal Integrity
    Minsu Kim, Hyunwook Park, Seongguk Kim, Keeyoung Son, Subin Kim, Kyunjune Son, Seonguk Choi, Gapyeol Park, and Joungho Kim
    In 2020 IEEE 29th Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS) 2020
  4. Deep Neural Network-based Lumped Circuit Modeling using Impedance Curve
    Daehwan Lho, Hyunwook Park, Seongguk Kim, Taein Shin, Keunwoo Kim, Kyungjune Son, Hyungmin Kang, Boogyo Sim, Keeyoung Son, Minsu Kim, and Joungho Kim
    In 2020 IEEE Electrical Design of Advanced Packaging and Systems (EDAPS) 2020