Najnowsze publikacje

• Klaudia Bałazy, Julian McAuley, Jacek Tabor, A Deeper Look into the Limitations of Early-Exit Architectures for Single and Multi-label Classification, International Conference on Computational Science [ICCS], (2025), 179–193
• Klaudia Bałazy, Mohammadreza Banaei, Karl Aberer, Jacek Tabor, LoRA-XS: low-rank adaptation with extremely small number of parameters, European Conference on Artificial Intelligence [ECAI], (2025), 3194 - 3201
• Patryk Marszałek, Klaudia Bałazy, Jacek Tabor, Tomasz Kuśmierczyk, Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRA, Empirical Methods in Natural Language Processing [EMNLP](MAIN), (2025), 1260-1271
• Bartosz Wójcik, Marcin Przewięźlikowski, Filip Szatkowski, Maciej Wołczyk, Klaudia Bałazy, Bartłomiej Krzepkowski, Igor Podolak, Jacek Tabor, Marek Śmieja, Tomasz Trzciński, Zero time waste in pre-trained early exit neural networks, Neural Networks 168 (2023), 580-601
• Klaudia Bałazy, Łukasz Struski, Marek Śmieja, Jacek Tabor, r-softmax: Generalized Softmax with Controllable Sparsity Rate, International Conference on Computational Science [ICCS] Lecture Notes in Computer Science, vol 14074. Springer, Cham (2023), 137-145