Junyoung Park

Junyoung Park

Senior AI Researcher · Qualcomm AI Research

Efficient LLM Inference · KV Cache Optimization · Reinforcement Learning · Neural Combinatorial Optimization

CV Google Scholar GitHub Email

Latest News

  • Mar 2026 CAOTE accepted to ICLR 2026 Workshop MemAgents.
  • Mar 2026 QuoKA (query-oriented KV selection for efficient LLM prefill) accepted to ICLR 2026.
  • Sep 2025 Two papers accepted to NeurIPS 2025: KeyDiff (KV cache eviction for long-context LLM inference) and PARCO (parallel autoregressive models for multi-agent combinatorial optimization).
  • Aug 2025 Routefinder accepted to TMLR 2025.
  • Jul 2025 RL4CO accepted to KDD 2025. Check out rl4co.ai4co.org.
  • Mar 2024 Recursive Speculative Decoding accepted to the LLM Agents Workshop at ICLR 2024.
  • Oct 2023 Started as Senior AI Researcher at Qualcomm AI Research to work on efficient LLM.

Publications

ICLR 2026
QuoKA: Query-Oriented KV Selection for Efficient LLM Prefill
Dalton Jones, Junyoung Park, Matthew J Morse, Mingu Lee, Matthew Harper Langston, Christopher Lott
[paper]
NeurIPS 2025
KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments
Junyoung Park, Dalton Jones, Matthew Morse, Raghavv Goel, Mingu Lee, Christopher Lott
[paper]
NeurIPS 2025
PARCO: Parallel Autoregressive Models for Multi-Agent Combinatorial Optimization
Federico Berto, Chuanbo Hua, Laurin Luttmann, Jiwoo Son, Junyoung Park, Kyuree Ahn, Changhyun Kwon, Jinkyoo Park
[paper]
KDD 2025
RL4CO: A Unified Reinforcement Learning for Combinatorial Optimization Library
Federico Berto, Chuanbo Hua, Junyoung Park, Minsu Kim, Hyeonah Kim, Jiwoo Son, Haeyeon Kim, Joungho Kim, Jinkyoo Park
[paper] [website]
ICLR Workshop 2026
CAOTE: KV Caching through Attention Output Error-Based Token Eviction
Raghavv Goel, Junyoung Park, Mukul Gagrani, Dalton Jones, Matthew Morse, Harper Langston, Mingu Lee, Christopher Lott
Transportation Science 2025
Genetic Algorithms with Neural Cost Predictor for Solving Hierarchical Vehicle Routing Problems
Abhay Sobhan, Junyoung Park, Jinkyoo Park, Changhyun Kwon
TMLR 2025
Routefinder: Towards Foundation Models for Vehicle Routing Problems
Federico Berto, Chuanbo Hua, Nayeli Gast Zepeda, André Hottung, Niels Wouda, Leon Lan, Junyoung Park, Kevin Tierney, Jinkyoo Park
[paper]
CVPR Workshop 2024
On Speculative Decoding for Multimodal Large Language Models
Mukul Gagrani, Raghavv Goel, Wonseok Jeon, Junyoung Park, Mingu Lee, Christopher Lott
[paper]
ICLR Workshop 2024
Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs
Raghavv Goel, Mukul Gagrani, Wonseok Jeon, Junyoung Park, Mingu Lee, Christopher Lott
[paper]
ICLR Workshop 2024
Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement
Wonseok Jeon, Mukul Gagrani, Raghavv Goel, Junyoung Park, Mingu Lee, Christopher Lott
[paper]
MSEC 2023
Generating Dispatching Rules for the Interrupting Swap-Allowed Blocking Job Shop Scheduling Problem Using Graph Neural Network and Reinforcement Learning
Vivian Wen Hui Wong, Sang Hun Kim, Junyoung Park, Jinkyoo Park, Kincho H. Law
[paper]
ICLR 2023
Neuro CROSS Exchange: Learning to CROSS Exchange to Solve Realistic Vehicle Routing Problems
Junyoung Park, Minjun Kim, Jinkyoo Park
[paper]
AAMAS 2023
Learn to Solve the Min-Max Multiple Traveling Salesmen Problem with Reinforcement Learning
Junyoung Park, Changhyun Kwon, Jinkyoo Park
arXiv 2023
FOCA: First-Order Context-Based Adaptation for Generalizing to New Dynamical Systems
Junyoung Park, Federico Berto, Arec Jamgochian, Mykel J. Kochenderfer, Jinkyoo Park
arXiv 2023
Learning Context-Aware Adaptive Solvers to Accelerate Convex Quadratic Programming
Haewon Jung, Junyoung Park, Jinkyoo Park
[paper]
NeurIPS 2022
Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimization
Minsoo Kim, Junyoung Park, Jinkyoo Park
[paper] [code]
ICLR 2022
Convergent Graph Solvers
Junyoung Park, Jinhyun Choo, Jinkyoo Park
[paper] [code]
arXiv 2022
Continuous-Depth Neural Models for Dynamic Graph Prediction
Michael Poli, Stefano Massaroli, Clayton M Rabideau, Junyoung Park, Atsushi Yamashita, Hajime Asama, Jinkyoo Park
arXiv 2022
ScheduleNet: Learn to Solve Multi-Agent Scheduling Problems with Reinforcement Learning
Junyoung Park, Sanjar Bakhtiyar, Jinkyoo Park
IJPR 2021
Learning to Schedule Job-Shop Problems: Representation and Policy Learning Using Graph Neural Network and Reinforcement Learning
Junyoung Park, Jaehyeong Chun, Sang Hun Kim, Youngkook Kim, Jinkyoo Park
[paper] [top-cited 2021/22] IF = 8.568
DLGMA @ AAAI 2020
Graph Neural Ordinary Differential Equations
Michael Poli, Stefano Massaroli, Junyoung Park, Atsushi Yamashita, Hajime Asama, Jinkyoo Park
[paper] [code]
IEEE Trans. Sustainable Energy 2019
Wind Field-Based Short-Term Turbine Response Forecasting by Stacked Dilated Convolutional LSTMs
Seongcheol Woo, Junyoung Park, Jinkyoo Park, Lance Manuel
IF = 9
Energy 2019
Physics-Induced Graph Neural Network: An Application to Wind-Farm Power Estimation
Junyoung Park, Jinkyoo Park
[paper] [code] [slides] IF = 8.857
IEEE Power & Energy Society 2018
Predicting Wind Turbine Power and Load Outputs by Multi-Task Convolutional LSTM Model
Seongcheol Woo, Junyoung Park, Jinkyoo Park

Education

Ph.D. — KAIST
Industrial & Systems Engineering · Mar 2016 – Feb 2023
Advisor: Jinkyoo Park
Thesis: Applications of graph neural networks in modeling and decision-making of dynamic networked systems (Best Dissertation Award, College of Engineering, 2023)
B.S. — KAIST
Industrial & Systems Engineering · Business and Technology Management (Double Major)
Feb 2011 – Feb 2016 · National Excellence Scholarship (Fully Funded)