Jaehyun Nam
Ph.D. student at KAIST
KAIST AI
jaehyun.nam [AT] kaist.ac.kr
About
I am a Ph.D. student at KAIST, advised by Prof. Jinwoo Shin. My research interests are centered on integrating large language models (LLMs) into a broad range of applications, leveraging their in-context learning and reasoning capabilities. My recent work specifically focuses on applying LLMs in tabular data analysis and molecular domains.
Topics of interest (publications with overlap):
- Large Language Models: ICLR'24, ICML'24, COLM'24, NeurIPS'24, NeurIPSW'24
- Tabular Learning: ICLR'23, COLM'24, NeurIPS'24
- AI for Science: TMLR'24, ICML'24, NeurIPSW'24
Publications
(*: Equal contribution)
An Efficient Tokenization for Molecular Language Models
Seojin Kim, Jaehyun Nam, Jinwoo Shin
NeurIPS Workshop on AI for New Drug Modalities (NeurIPSW-AIDrugX), 2024
Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning
Jaehyun Nam*, Kyuyoung Kim*, Seunghyuk Oh, Jihoon Tack, Jaehyung Kim, Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2024
Tabular Transfer Learning via Prompting LLMs
Jaehyun Nam, Woomin Song, Seong Hyeon Park, Jihoon Tack, Sukmin Yun, Jaehyung Kim, Kyu Hwan Oh, Jinwoo Shin
Conference on Language Modeling (COLM), 2024
ICML Workshop on Efficient Systems for Foundation Models (ICMLW-ES-FoMo), 2023
Data-Efficient Molecular Generation with Hierarchical Textual Inversion
Seojin Kim, Jaehyun Nam, Sihyun Yu, Younghoon Shin, Jinwoo Shin
International Conference on Machine Learning (ICML), 2024
NeurIPS Workshop on New Frontiers of AI for Drug Discovery and Development (NeurIPSW-AI4D3), 2023
Holistic Molecular Representation Learning via Multi-view Fragmentation
Seojin Kim*, Jaehyun Nam*, Junsu Kim, Hankook Lee, Sungsoo Ahn, Jinwoo Shin
Transactions on Machine Learning Research (TMLR), 2024
ICLR Workshop on Machine Learning for Materials (ICLRW-ML4Materials), 2023
SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs
Jaehyung Kim, Jaehyun Nam, Sangwoo Mo, Jongjin Park, Sang-Woo Lee, Minjoon Seo, Jung-Woo Ha, Jinwoo Shin
International Conference on Learning Representations (ICLR), 2024
STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables
Jaehyun Nam, Jihoon Tack, Kyungmin Lee, Hankook Lee, Jinwoo Shin
International Conference on Learning Representations (ICLR), 2023, Spotlight Presentation (280/4956=5.6%)
NeurIPS Workshop on Table Representation Learning (NeurIPSW-TRL), 2022
Bronze Prize, Samsung Humantech Paper Awards, 2023
Recipient, Google Conference Scholarships (APAC), 2023
Travel Award, International Conference on Learning Representations (ICLR), 2023
Grand Prize, KAIST-Samsung Electronics Industry-Academia Cooperation Paper Award, 2023
An Efficient Tokenization for Molecular Language Models
Seojin Kim, Jaehyun Nam, Jinwoo Shin
NeurIPS Workshop on AI for New Drug Modalities (NeurIPSW-AIDrugX), 2024
Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning
Jaehyun Nam*, Kyuyoung Kim*, Seunghyuk Oh, Jihoon Tack, Jaehyung Kim, Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2024
Tabular Transfer Learning via Prompting LLMs
Jaehyun Nam, Woomin Song, Seong Hyeon Park, Jihoon Tack, Sukmin Yun, Jaehyung Kim, Kyu Hwan Oh, Jinwoo Shin
Conference on Language Modeling (COLM), 2024
Data-Efficient Molecular Generation with Hierarchical Textual Inversion
Seojin Kim, Jaehyun Nam, Sihyun Yu, Younghoon Shin, Jinwoo Shin
International Conference on Machine Learning (ICML), 2024
Holistic Molecular Representation Learning via Multi-view Fragmentation
Seojin Kim*, Jaehyun Nam*, Junsu Kim, Hankook Lee, Sungsoo Ahn, Jinwoo Shin
Transactions on Machine Learning Research (TMLR), 2024
SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs
Jaehyung Kim, Jaehyun Nam, Sangwoo Mo, Jongjin Park, Sang-Woo Lee, Minjoon Seo, Jung-Woo Ha, Jinwoo Shin
International Conference on Learning Representations (ICLR), 2024
STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables
Jaehyun Nam, Jihoon Tack, Kyungmin Lee, Hankook Lee, Jinwoo Shin
International Conference on Learning Representations (ICLR), 2023, Spotlight Presentation (280/4956=5.6%)
Education
Korea Advanced Institute of Science and Technology (KAIST)
Ph.D. in Artificial IntelligenceSep. 2023 - Present
M.S. in Artificial IntelligenceMar. 2022 - Aug. 2023
Seoul National University (SNU)
B.S. in Industrial Engineering and Mathematical Sciences (minor)Mar. 2016 - Feb. 2022
Experience
Seoul National University (SNU)Mar. 2021 - Feb. 2022
Research Intern, hosted by Prof. Jung Hee Cheon
Korea Advanced Institute of Science and Technology (KAIST)Dec. 2020 - Jun. 2021
Research Intern, hosted by Prof. Chanyoung Park
SK HynixDec. 2020 - Feb. 2021
Intern, AI Solution
Industrial & Mathematical Data Analytics Research Center (IMDARC)Sep. 2020 - Dec. 2020
Research Intern, hosted by Prof. Woong Kook
Honors and Awards
Grand Prize ($5,000), KAIST-Samsung Electronics Industry-Academia Cooperation Paper Award Aug. 2023
Travel Award ($1,000), International Conference on Learning Representations (ICLR) May. 2023
Recipient ($3,000), Google Conference Scholarships (APAC) May. 2023
Bronze Prize ($5,000), Samsung Humantech Paper Awards Feb. 2023
Special Prize ($1,000), National Cryptograpy Contest Oct. 2021
Recipient ($6,000), Hanseong Scholarship for Gifted Students 2014 - 2016
Academic Services
Conference Reviewer NeurIPS, ICLR, AISTATS
Workshop Reviewer TRL@NeurIPS
Invited Talks
Semi-supervised Tabular Classification via In-context Learning of Large Language Models
Samsung Advanced Institue of Technology (Suwon, Korea)Jun. 2023
STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables
AI Expo Korea (Seoul, Korea)May. 2023
International Conference on Learning Representations (Kigali, Rwanda)May. 2023
Samsung Electronics Co., Ltd. (Virtual)Mar. 2023
MOGAM Institute for Biomedical Research (Virtual)Mar. 2023
Privacy-preserving Median Selection and Secure Aggregation in Federated Learning
Korean Mathematical Society Fall Meeting (Virtual)Oct. 2021
Special Prize, National Cryptography Contest, 2021