Klaudia Balazy

20 papers A* 1A 2Journal 11Unranked 6

Year	Rank	Type	Title / Venue / Authors
2025	—	`conf`	A Deeper Look into the Limitations of Early-Exit Architectures for Single and Multi-label Classification. ICCS (1) Klaudia Balazy, Julian J. McAuley, Jacek Tabor
2025	J	`jnl`	Detecting Data Contamination in LLMs via In-Context Learning. CoRR Michal Zawalski, Meriem Boubdir, Klaudia Balazy, Besmira Nushi, Pablo Ribalta
2025	A	`conf`	LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters. ECAI Klaudia Balazy, Mohammadreza Banaei, Karl Aberer, Jacek Tabor
2025	—	`conf`	Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRA. EMNLP (Findings) Patryk Marszalek, Klaudia Balazy, Jacek Tabor, Tomasz Kusmierczyk
2025	J	`jnl`	Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRA. CoRR Patryk Marszalek, Klaudia Balazy, Jacek Tabor, Tomasz Kusmierczyk
2024	J	`jnl`	LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters. CoRR Klaudia Balazy, Mohammadreza Banaei, Karl Aberer, Jacek Tabor
2023	J	`jnl`	Exploiting Transformer Activation Sparsity with Dynamic Inference. CoRR Mikolaj Piórczynski, Filip Szatkowski, Klaudia Balazy, Bartosz Wójcik
2023	—	`conf`	Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models. EACL (Findings) Mohammadreza Banaei, Klaudia Balazy, Artur Kasymov, Rémi Lebret, Jacek Tabor, Karl Aberer
2023	J	`jnl`	Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models. CoRR Mohammadreza Banaei, Klaudia Balazy, Artur Kasymov, Rémi Lebret, Jacek Tabor, Karl Aberer
2023	A	`conf`	Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks. EACL Piotr Gainski, Klaudia Balazy
2023	J	`jnl`	Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks. CoRR Piotr Gainski, Klaudia Balazy
2023	J	`jnl`	Zero time waste in pre-trained early exit neural networks. Neural Networks Bartosz Wójcik, Marcin Przewiezlikowski, Filip Szatkowski, Maciej Wolczyk, Klaudia Balazy, Bartlomiej Krzepkowski, Igor T. Podolak, Jacek Tabor, Marek Smieja, Tomasz Trzcinski
2023	—	`conf`	r-softmax: Generalized Softmax with Controllable Sparsity Rate. ICCS (2) Klaudia Balazy, Lukasz Struski, Marek Smieja, Jacek Tabor
2023	J	`jnl`	r-softmax: Generalized Softmax with Controllable Sparsity Rate. CoRR Klaudia Balazy, Lukasz Struski, Marek Smieja, Jacek Tabor
2021	—	`conf`	Direction is what you need: Improving Word Embedding Compression in Large Language Models. RepL4NLP@ACL-IJCNLP Klaudia Balazy, Mohammadreza Banaei, Rémi Lebret, Jacek Tabor, Karl Aberer
2021	J	`jnl`	Direction is what you need: Improving Word Embedding Compression in Large Language Models. CoRR Klaudia Balazy, Mohammadreza Banaei, Rémi Lebret, Jacek Tabor, Karl Aberer
2021	A*	`conf`	Zero Time Waste: Recycling Predictions in Early Exit Neural Networks. NeurIPS Maciej Wolczyk, Bartosz Wójcik, Klaudia Balazy, Igor T. Podolak, Jacek Tabor, Marek Smieja, Tomasz Trzcinski
2021	J	`jnl`	Zero Time Waste: Recycling Predictions in Early Exit Neural Networks. CoRR Maciej Wolczyk, Bartosz Wójcik, Klaudia Balazy, Igor T. Podolak, Jacek Tabor, Marek Smieja, Tomasz Trzcinski
2020	—	`conf`	Finding the Optimal Network Depth in Classification Tasks. ECML/PKDD (3) Bartosz Wójcik, Maciej Wolczyk, Klaudia Balazy, Jacek Tabor
2020	J	`jnl`	Finding the Optimal Network Depth in Classification Tasks. CoRR Bartosz Wójcik, Maciej Wolczyk, Klaudia Balazy, Jacek Tabor