Seokil Ham (함석일)
Tel: +82-42-350-7521
E-Mail: gkatjrdlf[at]kaist.ac.kr
Education
2023.3 - Present Ph.D. (School of Electrical Engineering), Korea Advanced Institute of Science Technology, South Korea
2021.3 - 2023.2 M.S. (School of Electrical Engineering), Korea Advanced Institute of Science Technology, South Korea
2017.3 - 2021.2 B.S. (School of Electrical Engineering), Chung-Ang University, South Korea
Research Interests
Machine Learning
Computer Vision
Diffusion Model
Publications
International Conference
S. Ham, J. Park, D.-J. Han, and J. Moon, "NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks ", Neural Information Process System (NeurIPS), Dec 2023.
D.-J. Han*, J. Park*, S. Ham, N. Lee and J. Moon, "Training Multi-Exit Architectures via Block-Dependent Losses for Anytime Inference," CVPR Workshop on Dynamic Neural Networks Meet Computer Vision, June 2022 (*=equal contribution)
International Journal
D.-J. Han*, J. Park*, S. Ham, N. Lee and J. Moon, "Improving Low-Latency Predictions in Multi-Exit Neural Networks via Block-Dependent Losses," IEEE Transactions on Neural Networks and Learning Systems, 2023. (*=equal contribution)