HeeJun Kim

Heejun Kim

📍 Korea Advanced Institute of Science and Technology (KAIST)
M.S. in Artificial Intelligence

Mail | CV | GitHub | Google Scholar

I am currently pursuing an M.S. in Artificial Intelligence at KAIST, conducting research on Reasoning and Efficient AI system at the Scalable and Efficient AI Lab under Prof. Sehoon Kim's supervision. AGI will usher in a new phase of human labor, and what counts as good AI judgment ultimately rests on human values. My work is dedicated to building AGI agents whose behavior aligns with those values.

Previously, I worked with Prof. Taesup Kim at Seoul National University and Prof. Sundong Kim at Gwangju Institute of Science and Technology, researching reasoning and LLM behavior.

I also worked as a visiting researcher at Forschungszentrum Jülich's INM-7 institute, directed by Prof. Simon B. Eickhoff, through the Korea-Germany Junior Research Fellowship, exploring the intersection of neuroscience and machine learning.

Education

Korea Advanced Institute of Science and Technology (KAIST) September 2026 – Present
M.S. in Artificial Intelligence
Gwangju Institute of Science and Technology (GIST) February 2020 – August 2026
B.S. in Electrical Engineering and Computer Science · GPA 4.2/4.5 (magna cum laude)
University of California, Berkeley (UC Berkeley) June 2024 – August 2024
Summer Session · GPA 4.0/4.0

Research Experience

Scalable and Efficient AI Lab
September 2026 - Present

Korea Advanced Institute of Science and Technology (KAIST) · Advisor: Prof. Sehoon Kim

  • Improving reasoning capabilities and accelerating inference in recursive architectures
Learning and Adaptation Algorithm Lab
Jan 2026 - August 2026

Seoul National University (SNU) · Advisor: Prof. Taesup Kim

  • Conducting research on Agentic Memory Using LLM Uncertainty Estimation
  • Studied internal behavioral mechanisms of LLMs underlying reasoning, hallucination, and memory recall
Data Science Lab
Feb 2025 - August 2026, Jan 2024 - June 2024

Gwangju Institute of Science and Technology (GIST) · Advisor: Prof. Sundong Kim

  • Researched test-time adaptation with reinforcement learning for self-improving reasoning capabilities of large language models on the Abstract Reasoning Corpus (ARC)
  • Investigated metacognition-driven strategies for helping large language models escape local minima in reasoning
Forschungszentrum Jülich
September 2024 - February 2025

Host Institute: INM-7, directed by Prof. Simon B. Eickhoff and contributed to Mathematical Neuroscience Group led by Dr. Oleksandr Popovych

  • Developed preprocessing pipeline for multi-modal MRI human connectome data using High-Performance Computing (HPC) and HyperThreading technology
  • Korea-Germany Junior Research Fellowship 2024 organized by Max Planck Korea

Publications

From Noise to Diversity: Random Embedding Injection in LLM Reasoning

Heejun Kim, Seungpil Lee, Jewon Yeom, Jaewon Sok, Seonghyeon Park, Jeongjae Park, Taesup Kim, Sundong Kim

NeurIPS 2026 | ICML 2026 Mechanistic Interpretability Workshop (Spotlight, 2.8% acceptance rate) | Paper

Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer

Jewon Yeom, Jaewon Sok, Heejun Kim, Seonghyeon Park, Jeongjae Park, Taesup Kim

NeurIPS 2026 | ICML 2026 Mechanistic Interpretability Workshop | Paper

On the Role of Proposal Support in Diffusion-Based Offline RL for Sequential Decision-Making

Yunho Kim, Jaehyun Park, Heejun Kim, Sejin Kim, Byung-Jun Lee, Sundong Kim

ICML 2026 DEMO Workshop | Paper

Honors & Awards

  • Government Scholarship, GIST (Mar 2020 - Aug 2026)
  • Government STEM Scholarship (Mar 2020 - Aug 2026)
  • Dean's List, College of Information and Computing, GIST (Spring 2025, Fall 2025)
  • Korea-Germany Junior Research Fellowship Program 2024 (Sep 2024 - Feb 2025)
    Fund: 12,000,000 KRW (8,197 EUR) by National Research Foundation of Korea (NRF), No. RS-2023-00254343.
  • GIST International Internship Support Program (Sep 2024 - Feb 2025)
  • Hyundai AI Challenge - Top 25/330 teams (Sep 2023 - Oct 2023)