Manuscript in preparation, 2026
Uncertainty quantification–based fine-tuning for large language models.
Recommended citation: Minoo Hong*, Hyungtak Lee*, et al. (2026). "Uncertainty Quantification-Based Fine-Tuning for Large Language Models." Manuscript in preparation. (*equal contribution)
Published in Sensors, 2023
A GAN architecture that generates training images together with bounding-box labels to augment scarce object-detection datasets.
Recommended citation: Hyungtak Lee, Seongju Kang, and Kwangsue Chung. (2023). "Robust Data Augmentation Generative Adversarial Network for Object Detection." Sensors, 23(1), 157. https://doi.org/10.3390/s23010157
Download Paper
Published in Journal of the Korea Institute of Information and Communication Engineering (JKIICE), 2022
An edge-computing-based IoT collaboration system for smart livestock farming.
Recommended citation: Chi-Hyun Ahn, Hyungtak Lee, and Kwangsue Chung. (2022). "IoT Collaboration System Based on Edge Computing for Smart Livestock System." Journal of the Korea Institute of Information and Communication Engineering.
Download Paper
Published in International Conference on Information and Communication Technology Convergence (ICTC), 2022
GAN-based dataset augmentation for fire-image object detection.
Recommended citation: Hyungtak Lee, Seongju Kang, and Kwangsue Chung. (2022). "Object Detection with Dataset Augmentation for Fire Images Based on GAN." 2022 13th International Conference on Information and Communication Technology Convergence (ICTC), pp. 2118-2123.
Download Paper
Published in Korea Computer Congress (KCC), 2022
A GAN-based framework for generating object-detection datasets.
Recommended citation: Hyungtak Lee, Seongju Kang, Jaegi Hwang, and Kwangsue Chung. (2022). "Object Detection Dataset Generation Framework using GAN." Korea Computer Congress (KCC).
Download Paper
Korean patent KR 10-2931826, 2026
Korean patent KR 10-2931826 (registered Feb. 2026), co-inventor.
Recommended citation: Kwangsue Chung, Hyungtak Lee, Seongju Kang, and Jaegi Hwang. "Generative Adversarial Networks for Fire Data Augmentation." Korean Patent KR 10-2931826, registered Feb. 2026.