Byeonghu Na (나병후)
Ph.D Candidate
Applied Artificial Intelligence Laboratory (AAILAB) (Prof. Il-Chul Moon)
Department of Industrial and Systems Engineering
KAIST (Korea Advanced Institute of Science and Technology)
E-mail: wp03052 [at] kaist [dot] ac [dot] kr (or) byeonghu.na [at] kaist [dot] ac [dot] kr
[Github] [LinkedIn] [Google Scholar]
Research Interest
Deep Generative Model: Diffusion Model, Variational Autoencoder
Insufficient/incomplete Dataset: Learning with Noisy Labels, Domain Adaptation, Active Learning, Positive-Unlabeled Learning
Selected Publication
[3] Label-Noise Robust Diffusion Models (TDSM)
Byeonghu Na, Yeongmin Kim, HeeSun Bae, Jung Hyun Lee, Se Jung Kwon, Wanmo Kang, and Il-Chul Moon
ICLR 2024 (The Twelfth International Conference on Learning Representations)
[2] Maximum Likelihood Training of Implicit Nonlinear Diffusion Models (INDM)
Dongjoun Kim*, Byeonghu Na*, Se Jung Kwon, Dongsoo Lee, Wanmo Kang, and Il-Chul Moon
NeurIPS 2022 (The Conference on Neural Information Processing Systems)
[1] Deep Generative Positive-Unlabeled Learning under Selection Bias (VAE-PU)