Byeonghu Na (나병후)

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.

Selected Publication

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)

• [paper] [code]

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)

• [paper] [code]