| Uncertainty-based offline reinforcement learning with diversified q-ensemble G An, S Moon, JH Kim, HO Song Advances in neural information processing systems 34, 7436-7447, 2021 | 198 | 2021 |
| Parsimonious black-box adversarial attacks via efficient combinatorial optimization S Moon, G An, HO Song International conference on machine learning, 4636-4645, 2019 | 142 | 2019 |
| Direct Preference-based Policy Optimization without Reward Modeling G An, J Lee, X Zuo, N Kosaka, KM Kim, HO Song Advances in Neural Information Processing Systems 36, 2024 | 5 | 2024 |
| Preemptive image robustification for protecting users against man-in-the-middle adversarial attacks S Moon, G An, HO Song Proceedings of the AAAI Conference on Artificial Intelligence 36 (7), 7823-7830, 2022 | 5 | 2022 |
| Designing an offline reinforcement learning objective from scratch. G An, J Lee, X Zuo, N Kosaka, KM Kim, HO Song arXiv preprint arXiv:2301.12842, 2023 | 1 | 2023 |
| Method and apparatus for classification using neural network SJ Park, HO Song, AN Gaon, HAN SeungJu US Patent 11,967,124, 2024 | | 2024 |
| Image recognition method and apparatus, image preprocessing apparatus, and method of training neural network KIM Jang-Hyun, HO Song, C Wonho, M Seungyong, AN Gaon, H Jeong US Patent 11,921,818, 2024 | | 2024 |
| Optimal channel selection with discrete QCQP Y Jeong, D Lee, G An, C Son, HO Song International Conference on Artificial Intelligence and Statistics, 7915-7941, 2022 | | 2022 |
| Succinct Network Channel and Spatial Pruning via Discrete Variable QCQP Y Jeong, D Lee, G An, C Son, HO Song | | 2020 |
| Exploiting Safe Spots in Neural Networks for Preemptive Robustness and Out-of-Distribution Detection S Moon, G An, HO Song | | 2020 |
