| Learning to balance: Bayesian meta-learning for imbalanced and out-of-distribution tasks HB Lee*, H Lee*, D Na*, S Kim, M Park, E Yang, SJ Hwang ICLR 2020, 2019 | 138 | 2019 |
| Help: Hardware-adaptive efficient latency prediction for nas via meta-learning H Lee, S Lee, S Chong, SJ Hwang arXiv preprint arXiv:2106.08630, 2021 | 58* | 2021 |
| Rapid neural architecture search by learning to generate graphs from datasets H Lee*, E Hyung*, SJ Hwang ICLR 2021, 2021 | 55 | 2021 |
| A survey of supernet optimization and its applications: Spatial and temporal optimization for neural architecture search S Cha, T Kim, H Lee, SY Yun arXiv preprint arXiv:2204.03916, 2022 | 15* | 2022 |
| Diffusion-based neural network weights generation B Soro, B Andreis, H Lee, S Chong, F Hutter, SJ Hwang arXiv preprint arXiv:2402.18153, 2024 | 11 | 2024 |
| DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models S An, H Lee, J Jo, S Lee, SJ Hwang arXiv preprint arXiv:2305.16943, 2023 | 11 | 2023 |
| A Study on Knowledge Distillation from Weak Teacher for Scaling Up Pre-trained Language Models H Lee, R Hou, J Kim, D Liang, SJ Hwang, A Min arXiv preprint arXiv:2305.18239, 2023 | 8 | 2023 |
| Task-Adaptive Neural Network Search with Meta-Contrastive Learning W Jeong, H Lee, G Park, E Hyung, J Baek, SJ Hwang Advances in Neural Information Processing Systems 34, 21310-21324, 2021 | 8 | 2021 |
| Online Hyperparameter Meta-Learning with Hypergradient Distillation HB Lee, H Lee, J Shin, E Yang, T Hospedales, SJ Hwang arXiv preprint arXiv:2110.02508, 2021 | 7 | 2021 |
| Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets H Lee, S An, M Kim, SJ Hwang The Eleventh International Conference on Learning Representations, 0 | 5* | |
| Lightweight Neural Architecture Search with Parameter Remapping and Knowledge Distillation H Lee, S An, M Kim, SJ Hwang First Conference on Automated Machine Learning (Late-Breaking Workshop), 2022 | 1 | 2022 |
| Co-training and Co-distillation for Quality Improvement and Compression of Language Models H Lee, R Hou, J Kim, D Liang, H Zhang, SJ Hwang, A Min arXiv preprint arXiv:2311.02849, 2023 | | 2023 |
Sung Ju HwangKAIST, DeepAutoEmail yang diverifikasi di kaist.ac.kr