Yeongmin Kim
I am currently in 3rd year of an integrated MS/Ph.D. program advised by Prof. Il-Chul Moon at the Korea Advanced Institute of Science and Technology (KAIST). I completed my B.S. in ISysE & CS in February 2022 from KAIST. I was born in Korea on June 17th, 1999.
My research focuses on generative models, with particular interests in fundamental modeling aspects such as parameterization, inference, and optimization. I am also interested in downstream tasks such as image-to-image translation and unsupervised representation learning.
I am always open to free discussions and collaborations related to generative models. Please feel free to contact me.
Contact: alsdudrla10@kaist.ac.kr
Hompage: Google Scholar, Github
Educations
KAIST, Daejeon, Korea, MS. (Mar. 2022 ~ Feb. 2023)
Department of Industrial & Systems Engineering (ISysE)
Transfer to Integrated program.
KAIST, Daejeon, Korea, Integrated MS. & Ph.D. (Mar. 2023 ~)
Graduate School of Data Science (GSDS)
Publications
(*: Equal contribution, C: Conferences, P: Preprint, W: Workshop)
2024
[C6] Diffusion Rejection Sampling
Byeonghu Na, Yeongmin Kim, Minsang Park, Donghyeok Shin, Wanmo Kang, Il-Chul Moon
International Conference on Machine Learning (ICML 2024)
[C5] Training Unbiased Diffusion Models From Biased Dataset [pdf]
Yeongmin Kim, Byeonghu Na, Minsang Park, JoonHo Jang, Dongjun Kim, Wanmo Kang, Il-Chul Moon
International Conference on Learning Representations (ICLR 2024)
[C4] Label-Noise Robust Diffusion Models [pdf]
Byeonghu Na, Yeongmin Kim, HeeSun Bae, Jung Hyun Lee, Se Jung Kwon, Wanmo Kang, Il-Chul Moon
International Conference on Learning Representations (ICLR 2024)
2023
[C3] Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models [pdf][code][media1][media2]
Dongjun Kim*, Yeongmin Kim*, Se Jung Kwon, Wanmo Kang, Il-Chul Moon
International Conference on Machine Learning (ICML 2023 )
Oral Presentation (Top 2.37%)
[C2] SAAL: Sharpness-Aware Active Learning [pdf]
Yoon-Yeong Kim*, Youngjae Cho*, JoonHo Jang, Byeonghu Na, Yeongmin Kim, Kyungwoo Song, Wanmo Kang, Il-Chul Moon
International Conference on Machine Learning (ICML 2023 )
2022
[W1] Unsupervised Controllable Generation with Score-based Diffusion Models: Disentangled Latent Code Guidance [pdf]
Yeongmin Kim, Dongjun Kim, HyeonMin Lee, Il-Chul Moon
NeurIPS 2022 Workshop on Score-Based Methods
2021
[C1] Predict Sequential Credit Card Delinquency with VaDE-Seq2Seq [pdf]
Yeongmin Kim, Youngjae Cho, Hanbit Lee, Il-Chul Moon
2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)