Latest News
[3/2024] "Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement" got accepted to Workshop on LLM Agents at ICLR 2024.
[2/2024] Check out the work from our group "Direct Alignment of Draft Model for Speculative Decoding with Chat-Fined-Tuned LLMs".
[1/2024] "Generating Dispatching Rules for the Interrupting Swap-Allowed Blocking Job Shop Problem Using Graph Neural Network and Reinforcement Learning" got accepted to Journal of Manufacturing Science and Engineering.
[12/2023] RL4CO: an extensive reinforcement learning for combinatorial optimization benchmark
(rl4.co) has been accepted as an oral presentation at the NeurIPS 2023 GLFrontiers Workshop!
[10/2023] I started as Senior Machine Learning Engineer at Qualcomm AI Research to work on efficient LLM!
[03/2023] "Prognosis prediction for glioblastoma multiforme patients using machine learning approaches: development of the clinically applicable model" got accepted to Radiotherapy and Oncology!
[02/2023] "Generating Dispatching Rules for the interrupting Swap-Allowed Blocking Job Shop Scheduling Problem Using
Graph Neural Network and Reinforcement Learning" got accepted to MSEC 2023!
[01/2023] "Neuro CROSS exchange: Learning to CROSS exchange to solve realistic vehicle routing problems" got accepted to ICLR 2023!
[01/2023] "Learn to solve the min‑max multiple traveling salesmen problem with reinforcement learning" got accepted to AAMAS 2023.
---
Education
---
- Mar 2016 \~ Feb 2023
- Industrial & Systems Engineering
- Advisor: [Jinkyoo Park](http://silab.kaist.ac.kr)
- Thesis: Applications of graph neural networks in modeling and decision-making of dynamic networks (Best Dissertation Award)
- Feb 2011 \~ Feb 2016
- Industrial & Systems Engineering
- Business and Technology Management (Double Major)
- Fully Funded by Korea Scholarship Foundation via National Excellence Scholarship
---
Selected Papers (*: Equal Contribution)
---
- Vivian Wen Hui Wong, Sang Hun Kim, Junyoung Park, Jinkyoo Park, and Kincho H. Law. _Generating Dispatching Rules for the interrupting Swap-Allowed Blocking Job Shop Scheduling Problem Using
Graph Neural Network and Reinforcement Learning_. MSEC 2023.
- Junyoung Park\*, Minjun Kim\*, and Jinkyoo Park. _Neuro CROSS Exchange: Learning to CROSS Exchange to
Solve Realistic Vehicle Routing Problems_. ICLR 2023. [paper]
- Junyoung Park, Changhyun Kwon, Jinkyoo Park, _Learn to solve the min‐max multiple traveling salesmen
problem with reinforcement learning_. AAMAS 2023.
- Junyoung Park, Federico Berto, Arec Jamgochian, Mykel J. Kochenderfer, and Jinkyoo Park, _FOCA:
First‐order Context‐based Adaptation for Generalizing to New Dynamical Systems_, arxiv 2023.
- Haewon Jung, Junyoung Park, and Jinkyoo Park, _Learning context‐aware adaptive solvers to accelerate
convex quadratic programming_, Arxiv 2023. [paper]
- Minsu Kim, Junyoung Park, and Jinkyoo Park, _Sym‐NCO: Leveraging Symmetricity for Neural
Combinatorial Optimization_, NeurIPS 2022. [paper] [code]
- Junyoung Park, Jinhyun Choo, and Jinkyoo Park, _Convergent Graph Solvers_, ICLR 2022. [paper] [code]
- Junyoung Park, Jaehyeong Chun, Sang Hun Kim, Youngkook Kim, and Jinkyoo Park, _Learning to schedule
job‐shop problems: representation and policy learning using graph neural network and reinforcement learning_,
International Journal of Production Research (IJPR) 2021 (IF = 8.568) Top-cited article published in
2021/22 (certificate) [paper]
- Michael Poli, Stefano Massaroli, Junyoung Park, Atsushi Yamashita, Hajime Asama, and Jinkyoo Park, _Graph neural ordinary differential equations_, Arxiv 2019. [paper] [code]
- Seongcheol Woo, Junyoung Park, Jinkyoo Park, and Lance Manuel, _Wind field‐based short‐term turbine
response forecasting by stacked dilated convolutional LSTMs_, IEEE Transactions on Sustainable Energy 2019 (IF = 9).
- Junyoung Park, Jinkyoo Park, _Physics‐induced graph neural network: An application to wind‐farm power
estimation_, Energy 2019 (IF = 8.857) [paper] [code] [slides]
