Joonkee Kim
I'm an LLM research engineer at Upstage, where I work on the Solar LLM series. Before that, I was at LG AI Research (2024–2026), where I contributed to the EXAONE models, from EXAONE 3.0 to EXAONE 4.5 and K-EXAONE.
I received my M.S. from the Graduate School of AI at KAIST, advised by Prof. Se-Young Yun, and my B.S. in Computer Science and Bio-Mechatronics from Sungkyunkwan University. My research focuses on LLM post-training and reinforcement learning.
Experience
Upstage
LLM Research Engineer · Solar LLM
Apr 2026 – Present
LG AI Research
LLM Research Engineer · EXAONE
Feb 2024 – Apr 2026
KAIST
M.S., Graduate School of AI · Advisor: Prof. Se-Young Yun
Mar 2022 – Feb 2024
Sungkyunkwan University
B.S., Computer Science and Bio-Mechatronics · Summa Cum Laude
Mar 2015 – Feb 2022
Publications
* equal contribution.
Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions
ICLR 2024 Spotlight
Re3val: Reinforced and Reranked Generative Retrieval
Findings of EACL 2024
PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning
NeurIPS 2023
HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning
Findings of EMNLP 2023
Toward Risk-Based Optimistic Exploration for Cooperative Multi-Agent Reinforcement Learning
AAMAS 2023
The Multimodality Cell Segmentation Challenge: Toward Universal Solutions
Nature Methods 2024
The StarCraft Multi-Agent Exploration Challenges: Learning Multi-Stage Tasks and Environmental Factors Without Precise Reward Functions
IEEE Access 2023
MEDIAR: Harmony of Data-Centric and Model-Centric for Multi-Modality Microscopy
NeurIPS 2022 Competition 1st Place
Technical Reports
As a contributor.
Solar Open 2 Technical Report · Upstage, 2026
EXAONE 4.5 Technical Report · LG AI Research, 2026
K-EXAONE Technical Report · LG AI Research, 2026
EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes · LG AI Research, 2025
EXAONE Deep: Reasoning Enhanced Language Models · LG AI Research, 2025
EXAONE 3.5: Series of Large Language Models for Real-world Use Cases · LG AI Research, 2024
EXAONE 3.0 7.8B Instruction Tuned Language Model · LG AI Research, 2024