| Demodice: Offline imitation learning with supplementary imperfect demonstrations GH Kim, S Seo, J Lee, W Jeon, HJ Hwang, H Yang, KE Kim International Conference on Learning Representations, 2021 | 128 | 2021 |
| Multi-view representation learning via total correlation objective HJ Hwang, GH Kim, S Hong, KE Kim Advances in Neural Information Processing Systems 34, 12194-12207, 2021 | 65 | 2021 |
| Variational interaction information maximization for cross-domain disentanglement HJ Hwang, GH Kim, S Hong, KE Kim Advances in Neural Information Processing Systems 33, 22479-22491, 2020 | 62 | 2020 |
| Regularized behavior cloning for blocking the leakage of past action information S Seo, HJ Hwang, H Yang, KE Kim Advances in Neural Information Processing Systems 36, 2128-2153, 2023 | 12 | 2023 |
| Information-theoretic state space model for multi-view reinforcement learning HJ Hwang, S Seo, Y Jang, S Kim, GH Kim, S Hong, KE Kim | 5 | 2023 |
| Mitigating covariate shift in behavioral cloning via robust stationary distribution correction S Seo, BJ Lee, J Lee, HJ Hwang, H Yang, KE Kim Advances in Neural Information Processing Systems 37, 109177-109201, 2024 | 4 | 2024 |
| 사전확률 갱신을 수행하는 교차 엔트로피 계획법 황형주， 장영수， 박재영， 김기응 정보과학회논문지 47 (1), 88-94, 2020 | | 2020 |
| CLEAR: An Information-Theoretic Framework for Distraction-Free Representation Learning in Visual Offline RL TW Guntara, DE Matsunaga, HJ Hwang, KE Kim | | |
| Contrast with Aggregation: A Scalable Framework for Multi-View Representation Learning HJ Hwang, AY Jin, H Kong, S Seo, S Hong, KE Kim | | |
