Scholar
Hoyeon Chang
Google Scholar ID: jD4MD7sAAAAJ
KAIST
Citations & Impact
Citations
117
H-index
3
i10-index
2
Publications
5
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Published research on the impact of vision-language adaptation on the safety of vision language models at ICLR 2025; published work on how large language models acquire factual knowledge during pretraining at NeurIPS 2024; published a paper on nonparametric decoding for generative retrieval in ACL 2023 Findings; received Best Poster Award at the 1st International NLP Workshop at KAIST, 2024; Outstanding Research Award, SNU Undergraduate Research Program, 2021; Hyoungae Scholarship, 2019 - 2021; Zayed Future Energy Prize in global high schools (Asia) category, 2016.
Research Experience
- Research Intern at KAIST LK Lab, Feb 2022 - Aug 2022 (Advisor: Minjoon Seo); Research Intern at SNU LDI Lab, Sep 2021 - Jan 2022 (Advisor: Seungwon Hwang); Research Intern at SNU CHANGlab, Dec 2020 - Feb 2021 (Advisor: Hyeshik Chang); SNU Undergraduate Research Program, May 2020 - Dec 2020 (Advisor: Young-Jae Seok). Also served as Teaching Assistant for Large Language Models at KAIST (Fall 2023) and Machine Learning Theory (Spring 2023).
Education
- Ph.D. in Artificial Intelligence, Korea Advanced Institute of Science and Technology (KAIST), Feb 2024 - Present; M.S. in Artificial Intelligence, KAIST, Sep 2022 - Feb 2024; B.S. in Biological Sciences and Electrical & Computer Engineering, Seoul National University, Mar 2018 - Aug 2022, Summa cum laude; Korea Science Academy of KAIST, Mar 2015 - Feb 2018.
Background
- Research interests include understanding how intelligent systems acquire and process knowledge from complex patterns, and developing systems that can perform robust variable binding and compositional reasoning. Specifically focused on analyzing language models to understand how they represent and utilize compositional knowledge, and interested in concepts from computational neuroscience, complex systems, philosophy, linguistics, psychology, etc.
Miscellany
- Native in Korean; fluent in English (TOEIC 925/990) and Japanese (JLPT N1 164/180); beginner in German and Spanish; founded and leads TMI (Thinking, Meaning, Intelligence) Group, an interdisciplinary academic group inspired by Norbert Wiener’s project on cybernetics, bringing together graduate students from philosophy, neuroscience, linguistics, computer science, physics, and education to explore fundamental questions about thinking, meaning, and intelligence through collaborative discussions and projects.
Co-authors