Scholar
Hyeong Kyu Choi
Google Scholar ID: MPBsFLEAAAAJ
University of Wisconsin-Madison, Korea University
Citations & Impact
Citations
335
H-index
9
i10-index
9
Publications
17
Co-authors
12
list available
Publications
Resume (English only)
Academic Achievements
- Selected Publications: 1. 'Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?' - NeurIPS Spotlight, 2025; 2. 'Mitigating Selection Bias with Node Pruning and Auxiliary Options' - ACL Main, 2025; 3. 'How Contaminated Is Your Benchmark? Measuring Dataset Leakage in Large Language Models with Kernel Divergence' - ICML, 2025; 4. 'PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning' - ICML, 2024; 5. 'NuTrea: Neural Tree Search for Context-guided Multi-hop KGQA' - NeurIPS, 2023; 6. 'TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers' - NeurIPS, 2022.
Research Experience
- Research Projects: Focus on the reliability of interactions within multi-agent systems, including coordination, debate, and collective reasoning; Other research areas include computer vision, natural language processing, knowledge graph reasoning, reinforcement learning, efficient deep learning, and financial machine learning.
Education
- Ph.D.: University of Wisconsin-Madison, Department of Computer Sciences, Advisor: Professor Sharon Yixuan Li; M.S.: Korea University, Department of Computer Science and Engineering, Advisor: Professor Hyunwoo J. Kim
Background
- Research Interests: Reliable and Safe AI Agents, Multi-Agent Systems; Professional Field: Computer Science; Bio: Hyeong-Kyu (Froilan) is a 3rd-year Ph.D. student at the University of Wisconsin-Madison's Computer Sciences department. His research goal is to make AI agents reliable in real-world applications.
Miscellany
- Personal Interest: Actively seeking internship opportunities for 2026 Summer!
