Jinhee Kim
Staff engineer at Samsung Research
Ph.D from Kim Jaechul Graduate School of Artificial Intelligence, KAIST (Aug 2024)
Contact: seharanul17@gmail.com
About Me
I am currently working on multimodal AI as a Staff Engineer at Samsung Research. I recently graduated with a Ph.D. from KAIST AI in August 2024, advised by Professor Jaegul Choo. I earned my B.S in Computer Science and Engineering at Korea University, graduating Summa Cum Laude.
Research interest
Large language models
Multimodal AI
Healthcare
Time-series analysis
Tabular data
User interaction
News
Nov 2024: Attending NeurIPS 2024 in Vancouver, Canada.
I will be presenting 🌞 EPIC at poster #2904 / East Exhibit Hall A-C / Wed 11 Dec 4:30 p.m. PST — 7:30 p.m. PST
Sep 2024: Paper accepted to NeurIPS 2024 🎉🎉
Sep 2024: Attending ECCV 2024 in Milan, Italy.
I will be presenting 🤖KeyBot at poster #108 during Poster Session 6 on Thur 3 Oct 4:30 p.m. — 6:30 p.m. CEST
July 2024: Attending ICML 2024 in Vienna, Austria 😀
July 2024: Paper accepted to ECCV 2024 🎉
June 2024: Successfully defended PhD dissertation in Artificial Intelligence at KAIST 🧑🎓
Honors and Awards
Student Travel Award, MICCAI, 2022
Best Poster Award, The AI Korea, 2022
Kyunghyun Cho Travel Grant, ICLR, 2020
Scholarship by College of Informatics, Korea University, 2019
Summa Cum Laude in Computer Science and Engineering, Korea University, 2019
Google Women Techmakers APAC Scholarship, Google, 2018
NAVER Scholarship, NAVER, 2018
Selected Publications [Google scholar]
EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language Models
J. Kim,* T. Kim,* and J. Choo (*: equal contributions)
Conference on Neural Information Processing Systems (NeurIPS), 2024.
🌞 Accepted with 25.8% acceptance rate.
Bones Can't Be Triangles: Accurate and Efficient Vertebrae Keypoint Estimation through Collaborative Error Revision
J. Kim,* T. Kim,* and J. Choo
(*: equal contributions)
European Conference on Computer Vision (ECCV), 2024.
😀Accepted with 27.9% acceptance rate.
Morphology-Aware Interactive Keypoint Estimation
J. Kim,* T. Kim,* T. Kim, J. Choo, D. Kim, B. Ahn, I. Song, and Y. Kim
(*: equal contributions)
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2022.
😀Accepted with 13% first-round provisional acceptance rate.
Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift
T. Kim,* J. Kim,* Y. Tae, C. Park, J. Choi, and J. Choo
(*: equal contributions)
International Conference on Learning Representations (ICLR), 2022.
😀Accepted with 32.3% acceptance rate.
D. Kim,* J. Kim,* T. Kim, T. Kim, Y. Kim, I. Song, B. Ahn, J. Choo, and D. Lee
(*: equal contributions)
Orthodontics & Craniofacial Research, 2021.
Missing Value Imputation of Time-Series Air-Quality Data via Deep Neural Networks
T. Kim, J. Kim, W. Yang, H. Lee, J. Choo
International journal of environmental research and public health, 2021.
T. Kim,* J. Kim,* H. Choi, E. Kim, B. Keum, Y. Jeen, H. Lee, H. Chun, S. Han, D. Kim, S. Kwon, J. Choo, and J. Lee (*: equal contributions)
Scientific Reports, 2021.
End-to-end multi-task learning of missing value imputation and forecasting in time-series data
J. Kim,* T. Kim,* J. Choi, and J. Choo (*: equal contributions)
International Conference on Pattern Recognition (ICPR), 2020.