Hyosoon Jang
Scholar

Hyosoon Jang

Google Scholar ID: NOJd3GEAAAAJ
Ph.D. student KAIST
Machine learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
51
 
H-index
4
 
i10-index
1
 
Publications
7
 
Co-authors
0
 
Contact
GitHubOpen ↗
Publications
2 items
Self-Training Large Language Models with Confident Reasoning
2025
Cited
0
Can LLMs Generate Diverse Molecules? Towards Alignment with Structural Diversity
arXiv.org · 2024
Cited
0
Resume (English only)
Academic Achievements
  • Published several papers, such as 'Self-Training Large Language Models with Confident Reasoning' and 'Pessimistic Backward Policy for GFlowNets'; received honors and awards including Postechian Fellowship (2024) and Presidential Science Scholarship (2024).
Research Experience
  • Involved in multiple research projects, including self-training large language models with confident reasoning, and learning energy decomposition for partial inference in GFlowNets.
Education
  • Ph.D. student, KAIST, 09.2025~ present, Advisor: Sungsoo Ahn
Background
  • Ph.D. student at KAIST, focusing on various types of generative models including large language models (LLMs), Generative Flow Networks (GFlowNets), and diffusion probabilistic models (DPMs) for inferring diverse solutions. Also interested in machine learning for medical and biological domains.
Miscellany
  • Invited to give talks at venues such as UMICH, ICLR, and MILA.
Co-authors
0 total
Co-authors: 0 (list not available)