Filip Szatkowski
Cited by
Cited by
Hypersound: Generating implicit neural representations of audio signals with hypernetworks
F Szatkowski, KJ Piczak, P Spurek, J Tabor, T Trzciński
arXiv preprint arXiv:2211.01839, 2022
Exploiting Transformer Activation Sparsity with Dynamic Inference
M Piórczyński, F Szatkowski, K Ba³azy, B Wójcik
arXiv preprint arXiv:2310.04361, 2023
Zero time waste in pre-trained early exit neural networks
B Wójcik, M Przewiȩ¼likowski, F Szatkowski, M Wo³czyk, K Ba³azy, ...
Neural Networks 168, 580-601, 2023
Hypernetworks build Implicit Neural Representations of Sounds
F Szatkowski, KJ Piczak, P Spurek, J Tabor, T Trzciński
Joint European Conference on Machine Learning and Knowledge Discovery in …, 2023
Progressive Latent Replay for Efficient Generative Rehearsal
S Pawlak, F Szatkowski, M Bortkiewicz, J Dubiński, T Trzciński
International Conference on Neural Information Processing, 457-467, 2022
Accelerated Inference and Reduced Forgetting: The Dual Benefits of Early-Exit Networks in Continual Learning
F Szatkowski, F Yang, B Twardowski, T Trzciński, J van de Weijer
arXiv preprint arXiv:2403.07404, 2024
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning
F Szatkowski, M Pyla, M Przewiź¼likowski, S Cygert, B Twardowski, ...
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2024
Sparser, Better, Deeper, Stronger: Improving Sparse Training with Exact Orthogonal Initialization
A Nowak, £ Gniecki, F Szatkowski, J Tabor
SADMoE: Exploiting Activation Sparsity with Dynamic-k Gating
F Szatkowski, B Wójcik, M Piórczyński, K Adamczewski
arXiv e-prints, arXiv: 2310.04361, 2023
The system can't perform the operation now. Try again later.
Articles 1–9