Postdoctoral Researcher @ KAIST, KAIST Institute for Robotics
Ph.D. @ KAIST ISE, Applied Artificial Intelligence Laboratory (AAILAB) (Prof. Il-Chul Moon)
E-mail: byeonghu.na [at] kaist [dot] ac [dot] kr (or) gwp03052 [at] gmail [dot] com
[CV] [Github] [LinkedIn] [Google Scholar]
Research Interest
My research interests focus on developing and applying probabilistic models to capture and analyze individual perspectives in complex real-world systems. I am particularly interested in generative models and adaptive training and inference, which provide principled approaches for modeling underlying structures across various data types, including vision, language, and multimodal systems.
News
[2025.08] Three papers (DATE, STG, BPO) accepted at NeurIPS 2025.
[2025.08] One paper accepted at NeurIPS 2025 GenProCC Workshop.
[2025.06] Recognized as an Outstanding Reviewer at CVPR 2025.
[2025.03] Joined the KAIST Institute for Robotics as a Postdoctoral Researcher.
[2025.02] Received the Best PhD Dissertation Award from KAIST College of Engineering.
[2024.12] DiffRS was awarded as one of the Winners of the Qualcomm Innovation Fellowship Korea (QIFK) 2024.
[2024.12] Successfully defended my Ph.D. dissertation! (Title: Improving Conditional Information Estimation for Diffusion-based Generative Models)
[▼ More]
[2024.12] DiffRS awarded Best Poster at the Samsung AI Forum 2024.
[2024.07] Awarded the Outstanding Champion Award and Innovation Award at the EgoPlan Challenge, ICML 2024 MFM-EAI Workshop.
[2024.01] Four papers (TDSM, TIW-DSM, RENT, UDIM) accepted at ICLR 2024.
[2023.12] Recognized as a Top Reviewer at NeurIPS 2023.
[2022.12] Recognized as a Top Reviewer at NeurIPS 2022.
[2022.11] INDM awarded Best Poster ast the Samsung AI Forum 2022.
[2022.09] Two papers (INDM, UADAL) accepted at NeurIPS 2022.
[2022.06] One paper (ORC) accepted at ICML 2022 SCIS Workshop.
[2021.04] Selected for the Chonghwan Educational Foundation Domestic Graduate Student Scholarship.
[2020.09] Joined NAVER Clova AI Research as a research intern.
[2020.09] Received a SIGIR Student Travel Grant.
[2020.08] Selected for the Young-Han Kim Global Leader Scholarship at KAIST.
Selected Publications
Training-free Safe Text Embedding Guidance for Text-to-Image Diffusion Models (STG)
Byeonghu Na, Mina Kang, Jiseok Kwak, Minsang Park, Jiwoo Shin, SeJoon Jun, Gayoung Lee, Jin-Hwa Kim, and Il-Chul Moon
NeurIPS 2025 (The Thirty-ninth Annual Conference on Neural Information Processing Systems)
Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models (DATE)
Byeonghu Na, Minsang Park, Gyuwon Sim, Donghyeok Shin, HeeSun Bae, Mina Kang, Se Jung Kwon, Wanmo Kang, and Il-Chul Moon
NeurIPS 2025 (The Thirty-ninth Annual Conference on Neural Information Processing Systems)
Diffusion Rejection Sampling (DiffRS)
Byeonghu Na, Yeongmin Kim, Minsang Park, Donghyeok Shin, Wanmo Kang, and Il-Chul Moon
ICML 2024 (The Forty-first International Conference on Machine Learning)
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)