I recently completed my M.S. in the Department of Industrial and Systems Engineering at KAIST, where I was advised by Prof. Hwanjun Song. I received my B.S. in Industrial Engineering from Yonsei University, where I worked as a research intern with Prof. Kyungwoo Song. I hold dual citizenship of the United States and the Republic of Korea, and I plan to apply to Ph.D. programs in Fall 2027 as a domestic applicant in the U.S.
My research focuses on efficient and scalable AI systems, with particular emphasis on optimization for large-scale deep learning models. I am interested in improving training and inference efficiency in large language models (LLMs) and vision–language models (VLMs), as well as developing robust and reliable AI systems that perform effectively under real-world constraints.
Publications
Robust Dataset Condensation using Supervised Contrastive Learning
Nicole Hee-Yeon Kim and Hwanjun Song
ICCV 2025, Main
[paper] [code]
Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages
Hyangsuk Min, Yuho Lee, Minjeong Ban, Jiaqi Deng, Nicole Hee-Yeon Kim, Taewon Yun, Hang Su, Jason Cai, Hwanjun Song
ACL 2025, Main
[paper] [code]
IMC: A Benchmark for Invariant Learning under Multiple Causes
Taero Kim, Seonggyun Lee, Joonseong Kang, Youngjun Choi, Wonsang Yun, Nicole Hee-Yeon Kim, Ziyu Chen, Lexing Xie, Kyungwoo Song
CVPR 2025 Workshop on Domain Generalization: Evolution, Breakthroughs, and Future Horizons, Best Paper Award
[paper] [code]
Learning to Verify Summary Facts with Fine-Grained LLM Feedback
Jihwan Oh, Jeonghwan Choi, Nicole Hee-Yeon Kim, Taewon Yun, Hwanjun Song
COLING 2025, Oral
[paper] [code]
Robust Dataset Condensation via Semi-Supervised Learning
Nicole Hee-Yeon Kim, Jeonghwan Choi, Yuho Lee, Hwanjun Song
KCC 2025, Oral (in Korean)
Improving Language Model Quality through LLM-based Fine-Grained Hallucinated Summary Generation
Jihwan Oh, Jeonghwan Choi, Nicole Hee-Yeon Kim, Hwanjun Song
Journal of Computing Practice, vol. 31(2), pp. 91-97. (in Korean)
[paper]
Robust Dataset Condensation via Supervised Contrastive Learning
Nicole Hee-Yeon Kim, Jeonghwan Choi, Yuho Lee, Hwanjun Song
KSC 2024, Oral (in Korean)
[paper]
Improving the Text Summary Quality Through Understanding the Hallucination Level of Summarization Using Large Language Models
Jihwan Oh, Jeonghwan Choi, Nicole Hee-Yeon Kim, Hwanjun Song
KCC 2024, Oral (in Korean)
[paper]
Patent
Patent Pending – KAIST Patent Registration ID: KR P2025-0286, Robust Dataset Condensation using Supervised Contrastive Learning
Honors and Awards
- Best Paper Award — CVPR 2025 Workshop, 2025
- KAIST Support Scholarship (Government-funded full tuition scholarship for M.S. program), 2024–Present
- Brain Korea 21 (BK21) Scholarship (Government-funded research scholarship for graduate students), 2024–Present
- Korea Computer Congress Outstanding Presentation Paper Award, 2024
- Yonsei Welfare Scholarship (Full tuition scholarship for B.S. program), 2019–2023
- 1st Place, Department of Industrial Engineering Promotional Video Contest, 2022
- University Innovation Support Scholarship, 2020–2021
- Teaching Assistant Scholarship for the Data Science Program, 2020–2021
- Yonsei Social Entrepreneurship Award, 2021