Haebin Shin
Scholar

Haebin Shin

Google Scholar ID: LCQIC0wAAAAJ
KAIST
Machine LearningNatural Language Processing
Citations & Impact
All-time
Citations
95
 
H-index
4
 
i10-index
3
 
Publications
17
 
Co-authors
12
list available
Resume (English only)
Academic Achievements
  • Published multiple papers including DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections, Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling, etc. Won several awards such as Stars of Tomorrow, 1st Place in NeurIPS 2020 NLC2CMD Challenge, etc. Holds three patents.
Research Experience
  • Research Intern at Microsoft Research (2024.09 – Present); Researcher at Samsung Research (2020.01 – 2024.09); Researcher at ESTsoft (2016.05 – 2019.12). Contributed to applied LLM systems for Galaxy AI.
Education
  • M.S. in Graduate School of AI, Korea Advanced Institute of Science & Technology (KAIST) (2022 – Present); B.S. in Computer Science, Sogang University (2013 – 2020)
Background
  • Graduate student at KAIST, specializing in natural language processing (NLP) and large language models (LLMs), advised by Prof. Minjoon Seo. Research interests lie in making LLMs more efficient and practical.