Scholar
Hyunseok Lee
Google Scholar ID: Ae4znVwAAAAJ
KAIST
Citations & Impact
Citations
17
H-index
2
i10-index
1
Publications
3
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- Publication: 'ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and Search'
- Publication: 'ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification', ICML 2025 (*equal contribution)
- Publication: 'ReMoDetect: Reward Models Recognize Aligned LLM's Generations', NeurIPS 2024 (*equal contribution)
- Qualcomm Innovation Fellowship Korea 2024 recipient
- 1st Place in Korean LLM Leaderboard with 'hyunseoki/ko-en-llama2-13b', Oct. 2023
Research Experience
- Research Intern, Microsoft Research Asia, July 2025 – Present
- Research Intern, Naver Cloud, Feb. 2025 – Jun. 2025
- Research Intern, Omnious AI, Jun. 2023 – Dec. 2023
- Conference Reviewer, NeurIPS
- Workshop Reviewer, Reasoning and Planning for LLMs @ ICLR
Background
- Second-year Ph.D. student at KAIST, advised by Prof. Jinwoo Shin
- Research Intern at Microsoft Research Asia
- Research interests focus on building self-aware and safe intelligence
- Developing Large Language Models (LLMs) with reasoning, agentic decision-making, and safety guarantees
- Broadly interested in continual pretraining of LLMs and their multilingual capabilities
- Topics of interest: LLM, LLM Reasoning, LLM-based Agents, LLM Safety
