Seungpil Lee
Scholar

Seungpil Lee

Google Scholar ID: iPfrGWAAAAAJ
Master Student, GIST
AGI
Citations & Impact
All-time
Citations
47
 
H-index
3
 
i10-index
1
 
Publications
10
 
Co-authors
0
 
Resume (English only)
Academic Achievements
  • 1. Can Large Language Models Develop Gambling Addiction?
  • arXiv preprint, 2025
  • 2. Solution Augmentation for ARC-AGI Problems Using GFlowNet: A Probabilistic Exploration Approach
  • Transactions on Machine Learning Research, 2025
  • 3. Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpus
  • ACM Transactions on Intelligent Systems and Technology (Accept with Minor Revision), 2024-2025
  • 4. Reasoning Abilities of Large Language Models through the Lens of Abstraction and Reasoning (Extended Abstract of the below paper)
  • NeurIPS Workshop on System-2 Reasoning at Scale, 2024-2025
  • 5. From Generation to Selection: Findings of Converting Analogical Problem-Solving into Multiple-Choice Questions
  • EMNLP Findings, 2024
Research Experience
  • Data Science and Artificial Intelligence Lab, GIST
  • March 2024 - Present
  • Graduate Research Assistant, Supervised by Prof. Sundong Kim
  • Working on Abstraction and Reasoning Corpus (ARC) challenge, Developing novel approaches for visual reasoning and abstract problem solving, Researching brain-inspired AI architectures for cognitive reasoning tasks
Education
  • 1. March 2025 - Present: Gwangju Institute of Science and Technology (GIST), Master's Degree in AI Convergence, Research focus: Brain-inspired AI, Visual Reasoning, Abstract Reasoning, Advisor: Prof. Sundong Kim
  • 2. March 2018 - December 2024: Gwangju Institute of Science and Technology (GIST), Bachelor's Degree in Electrical Engineering and Computer Science, Minor in Mathematics and Literature
Background
  • A passionate Master's student with a primary interest in brain-inspired AI and a broad curiosity that extends to other areas of artificial intelligence, including NLP and reinforcement learning. Additionally, maintains a keen interest in interdisciplinary subjects such as cognitive science and STS.
Co-authors
0 total
Co-authors: 0 (list not available)