| Revisiting random channel pruning for neural network compression Y Li, K Adamczewski, W Li, S Gu, R Timofte, L Van Gool Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2022 | 158 | 2022 |
| Dp-merf: Differentially private mean embeddings with randomfeatures for practical privacy-preserving data generation F Harder, K Adamczewski, M Park International conference on artificial intelligence and statistics, 1819-1827, 2021 | 150 | 2021 |
| Scaling laws for fine-grained mixture of experts J Krajewski, J Ludziejewski, K Adamczewski, M Pióro, M Krutul, ... arXiv preprint arXiv:2402.07871, 2024 | 100* | 2024 |
| Discrete tabu search for graph matching K Adamczewski, Y Suh, K Mu Lee Proceedings of the IEEE international conference on computer vision, 109-117, 2015 | 63 | 2015 |
| Hermite polynomial features for private data generation M Vinaroz, MA Charusaie, F Harder, K Adamczewski, MJ Park International Conference on Machine Learning, 22300-22324, 2022 | 38 | 2022 |
| Radial and directional posteriors for bayesian deep learning C Oh, K Adamczewski, M Park Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 5298-5305, 2020 | 34* | 2020 |
| Subgraph matching using compactness prior for robust feature correspondence Y Suh, K Adamczewski, K Mu Lee Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2015 | 29 | 2015 |
| Differentially Private Neural Tangent Kernels (DP-NTK) for Privacy-Preserving Data Generation Y Yang, K Adamczewski, X Li, DJ Sutherland, M Park Journal of Artificial Intelligence Research 81, 683-700, 2024 | 21 | 2024 |
| Differential privacy meets neural network pruning K Adamczewski, M Park arXiv preprint arXiv:2303.04612, 2023 | 13 | 2023 |
| Dirichlet pruning for convolutional neural networks K Adamczewski, M Park International Conference on Artificial Intelligence and Statistics, 3637-3645, 2021 | 10* | 2021 |
| How good is the Shapley value-based approach to the influence maximization problem? K Adamczewski, S Matejczyk, TP Michalak arXiv preprint arXiv:1409.7830, 2014 | 9* | 2014 |
| Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient J Ludziejewski, M Pióro, J Krajewski, M Stefaniak, M Krutul, J Małaśnicki, ... arXiv preprint arXiv:2502.05172, 2025 | 6 | 2025 |
| Adaglimpse: Active visual exploration with arbitrary glimpse position and scale A Pardyl, M Wronka, M Wołczyk, K Adamczewski, T Trzciński, B Zieliński European Conference on Computer Vision, 112-129, 2024 | 5 | 2024 |
| Bayesian importance of features (bif) K Adamczewski, F Harder, M Park arXiv preprint arXiv:2010.13872, 2020 | 5 | 2020 |
| Pre-Pruning and Gradient-Dropping Improve Differentially Private Image Classification K Adamczewski, Y He, M Park arXiv preprint arXiv:2306.11754, 2023 | 4 | 2023 |
| Shapley Pruning for Neural Network Compression K Adamczewski, Y Li, L Van Gool arXiv preprint arXiv:2407.15875, 2024 | 3 | 2024 |
| Neuron ranking--an informed way to condense convolutional neural networks architecture K Adamczewski, M Park arXiv preprint arXiv:1907.02519, 2019 | 3 | 2019 |
| One shot vs. iterative: Rethinking pruning strategies for model compression M Janusz, T Wojnar, Y Li, L Benini, K Adamczewski arXiv preprint arXiv:2508.13836, 2025 | 2 | 2025 |
| Lidar line selection with spatially-aware shapley value for cost-efficient depth completion K Adamczewski, C Sakaridis, V Patil, L Van Gool Conference on Robot Learning, 561-570, 2023 | 2 | 2023 |
| The Smoothed Pólya-Vinogradov Inequality. K Adamczewski, E Trevino Integers 15, A20, 2015 | 2 | 2015 |
Yumin SuhAtmanityVerified email at atmanity.io
