Biography
Research Scientist working on RLHF and AI alignment. Previously at Google DeepMind. 40+ publications.
Publications (2)
Transformer Architecture Scaling Laws for Scientific Text Classification
Journal of Artificial Intelligence Research
- Volume 13, Issue 1 — January 2024 (2024)
- Research Article
Author
We investigate scaling laws for transformer-based language models applied to scientific literature classification. Our experiments across 12 benchmark datasets demonstrate that model performance scales predictably with parameter count and training…
Research Article
DOI
Open Access
Peer Reviewed
Reinforcement Learning from Human Feedback: A Systematic Review
Journal of Artificial Intelligence Research
- Volume 12, Issue 4 — October 2023 (Special: LLMs) (2023)
- Review Article
Author
Corresponding Author
This systematic review examines 147 studies on reinforcement learning from human feedback (RLHF) published between 2017 and 2024. We identify key methodological trends, open challenges in reward modeling, and propose…
Review Article
DOI
Open Access
Peer Reviewed
Statistics
2
Publications
0
Journals
0
Version Contributions
Contact Information
Email:
ORCID:
Affiliation:
KAIST School of Computing, South Korea