FS
Filip Szatkowski
cs.LGcs.AIcs.CVcs.CLcs.SDeess.ASConditional computationcs.CRcs.NEcs.RO
On Valency
published · living versionsW_5txyfx4z·v1 · currentpublished
Preprints & journals
16 papers in the corpus · 2022–2026Shieldstral2607.25857v2 · Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli et al.2026 · 0 citationsarXiv
Robostral Navigate2607.20785v3 · Abdelaziz Bounhar, Abhijeet Somani, Aditi Kabra et al.2026 · 0 citationsarXiv
Beyond Classification: Dynamic Adapter Routing for Continual Multimodal Retrieval2605.31229v1 · Alicja Dobrzeniecka, Filip Szatkowski, Sebastian Cygert et al.2026 · 0 citationsarXiv
Universal Properties of Activation Sparsity in Modern Large Language Models2509.00454v2 · Filip Szatkowski, Patryk Bedkowski, Alessio Devoto et al.2025 · 0 citationsarXiv
Rethinking Calibration for Early-Exit Neural Networks2508.21495v3 · Piotr Kubaty, Filip Szatkowski, Grzegorz Choczy'nski et al.2025 · 0 citationsarXiv
ExpertSim: Fast Particle Detector Simulation Using Mixture-of-Generative-Experts2508.20991v1 · Patryk Bedkowski, Jan Dubi'nski, Filip Szatkowski et al.2025 · 1 citationarXiv
Efficient LLM Moderation with Multi-Layer Latent Prototypes2502.16174v4 · Maciej Chrabaszcz, Filip Szatkowski, Bartosz W'ojcik et al.2025 · 0 citationsarXiv
Exploring the Stability Gap in Continual Learning: The Role of the Classification Head2411.04723v2 · Wojciech \Lapacz, Daniel Marczak, Filip Szatkowski et al.2024 · 1 citationarXiv
Sparser, Better, Deeper, Stronger: Improving Sparse Training with Exact Orthogonal Initialization2406.01755v1 · Aleksandra Irena Nowak, \Lukasz Gniecki, Filip Szatkowski et al.2024 · 1 citationarXiv
Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers2403.07404v4 · Filip Szatkowski, Yaoyue Zheng, Fei Yang et al.2024 · 0 citationsarXiv
Zero time waste in pre-trained early exit neural networks.37837747 · Wójcik, Bartosz, Przewiȩźlikowski, Marcin, Szatkowski, Filip et al.2023 · 10 citationsNeural networks : the official journal of the International Neural Network Society. 2023;168:580-601
Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion2310.04361v4 · Filip Szatkowski, Bartosz W'ojcik, Miko\laj Pi'orczy'nski et al.2023 · 2 citationsarXiv
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning2308.09544v3 · Filip Szatkowski, Mateusz Pyla, Marcin Przewie'zlikowski et al.2023 · 14 citationsarXiv
Hypernetworks build Implicit Neural Representations of Sounds2302.04959v3 · Filip Szatkowski, Karol J. Piczak, Przemys\law Spurek et al.2023 · 15 citationsarXiv
HyperSound: Generating Implicit Neural Representations of Audio Signals with Hypernetworks2211.01839v2 · Filip Szatkowski, Karol J. Piczak, Przemys\law Spurek et al.2022 · 4 citationsarXiv
Progressive Latent Replay for efficient Generative Rehearsal2207.01562v2 · Stanis\law Pawlak, Filip Szatkowski, MichałBortkiewicz et al.2022 · 1 citationarXiv
Career total: 22 works. 16 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.