Yeongmin KIM > Member | 카이스트 응용인공지능 연구실

Research Interest

Deep generative models: parametrization, inference, optimization
DGM downstream task: controllable generation, unsupervised representation learning

Education

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea (Mar. 2023 ~ )

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea (Mar. 2022 ~ )

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea (Mar. 2017 - Feb. 2022)

Publication

International Conference

Yeongmin Kim, Byeonghu Na, JoonHo Jang, Minsang Park, Dongjun Kim, Wanmo Kang, Il-Chul Moon, Training Unbiased Diffusion Models From Biased Dataset, International Conference on Learning Representations (ICLR 2024), Vienna, Austria, May 7-11, 2024
Byeonghu Na, Yeongmin Kim, HeeSun Bae, Jung Hyun Lee, Se Jung Kwon, Wanmo Kang, Il-Chul Moon, Label-Noise Robust Diffusion Models, International Conference on Learning Representations (ICLR 2024), Vienna, Austria, May 7-11, 2024
Yoon-Yeong Kim*, Youngjae Cho*, JoonHo Jang, Byeonghu Na, Yeongmin Kim, Kyungwoo Song, Wanmo Kang, Il-Chul Moon, SAAL: Sharpness-Aware Active Learning, International Conference on Machine Learning (ICML 2023), Hawaii, USA, Jul 25-27, 2023
Dongjun Kim*, Yeongmin Kim*, Se Jung Kwon, Wanmo Kang, Il-Chul Moon, Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models, International Conference on Machine Learning (ICML 2023), Hawaii, USA, Jul 25-27, 2023 (Oral presentation)
Yeongmin Kim, Dongjun Kim., Hyeonmin Lee, & Il-Chul Moon (2022, December). Unsupervised Controllable Generation with Score-based Diffusion Models: Disentangled Latent Code Guidance. In Neurips 2022 workshops on Score Based Method.
Yeongmin Kim, Youngjae Cho, Hanbit Lee, & Il-Chul Moon (2021, October). Predict Sequential Credit Card Delinquency with VaDE-Seq2Seq. In 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC) (pp. 1159-1164). IEEE.

Award