| Relational knowledge distillation W Park, D Kim, Y Lu, M Cho Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2019 | 2274 | 2019 |
| Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities G Comanici, E Bieber, M Schaekermann, I Pasupat, N Sachdeva, I Dhillon, ... arXiv preprint arXiv:2507.06261, 2025 | 1337 | 2025 |
| Groupface: Learning latent groups and constructing group-based representations for face recognition Y Kim, W Park, MC Roh, J Shin Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020 | 141 | 2020 |
| GRPE: Relative Positional Encoding for Graph Transformer W Park*, WG Chang*, D Lee, J Kim, S Hwang ICLR2022 Machine Learning for Drug Discovery, 2022 | 112 | 2022 |
| BroadFace: Looking at Tens of Thousands of People at Once for Face Recognition Y Kim*, W Park*, J Shin European Conference on Computer Vision (ECCV), 2020 | 71 | 2020 |
| Prefixing attention sinks can mitigate activation outliers for large language model quantization S Son, W Park, W Han, K Kim, J Lee arXiv preprint arXiv:2406.12016, 2024 | 18 | 2024 |
| Multi-level Distance Regularization for Deep Metric Learning Y Kim*, W Park* Association for the Advancement of Artificial Intelligence (AAAI), 2021 | 17 | 2021 |
| Jaxpruner: A concise library for sparsity research JH Lee, W Park, NE Mitchell, J Pilault, JSO Ceron, HB Kim, N Lee, ... Conference on Parsimony and Learning, 515-528, 2024 | 16 | 2024 |
| Diversified Mutual Learning for Deep Metric Learning W Park*, W Kim*, K You, M Cho European Conference on Computer Vision, 709-725, 2020 | 11 | 2020 |
| Compression scaling laws: Unifying sparsity and quantization E Frantar, U Evci, W Park, N Houlsby, D Alistarh arXiv preprint arXiv:2502.16440, 2025 | 7 | 2025 |
| Discrete Infomax Codes for Supervised Representation Learning Y Lee, W Kim, W Park, S Choi Entropy 24 (4), 501, 2022 | 5 | 2022 |
| Rethinking pruning large language models: Benefits and pitfalls of reconstruction error minimization S Shin, W Park, J Lee, N Lee arXiv preprint arXiv:2406.15524, 2024 | 4 | 2024 |
| Breaking ReLU Barrier: Generalized MoEfication for Dense Pretrained Models J Lee, S Hwang, W Park, M Ji Proceedings of the 2024 Conference on Empirical Methods in Natural Language …, 2024 | 2 | 2024 |
| Lcirc: A recurrent compression approach for efficient long-form context and query dependent modeling in llms S An, J Sung, W Park, C Park, H Seo Proceedings of the 2025 Conference of the Nations of the Americas Chapter of …, 2025 | 1 | 2025 |
| Activation Quantization of Vision Encoders Needs Prefixing Registers S Kim, J Kim, T Yeom, W Park, K Kim, J Lee arXiv preprint arXiv:2510.04547, 2025 | | 2025 |
| Post-training quantization of vision encoders needs prefixing registers S Kim, J Kim, T Yeom, W Park, K Kim, J Lee | | 2025 |
| Regularizing Neural Networks via Stochastic Branch Layers W Park*, PH Seo*, B Han, M Cho Asian Conference on Machine Learning (ACML), 2019 | | 2019 |
Minsu ChoMu-Eun-Jae Endowed Chair Professor, Associate Professor of CSE & AI, POSTECHVerified email at postech.ac.kr
