mgr Klaudia Bałazy

Jednostki:

  • Wydział Matematyki i Informatyki UJ
  • Instytut Informatyki i Matematyki Komputerowej
  • Katedra Uczenia Maszynowego

Publikacje:

7.
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 vol. 168 (2023), 580-601
6.
Klaudia Bałazy, Łukasz Struski, Marek Śmieja, Jacek Tabor
r-softmax: Generalized Softmax with Controllable Sparsity Rate, International Conference on Computational Science [ICCS] vol. Lecture Notes in Computer Science, vol 14074. Springer, Cham (2023), 137-145
5.
Mohammadreza Banaei, Klaudia Bałazy, Artur Kasymov, Rémi Lebret, Jacek Tabor, Karl Aberer
Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models, European Association of Computational Linguistics [EACL] vol. Findings of the Association for Computational Linguistics: EACL 2023 (2023), 1788–1805
4.
Piotr Gaiński, Klaudia Bałazy
Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks, European Association of Computational Linguistics [EACL] vol. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics (2023), 2038–2048
3.
Klaudia Bałazy, Igor Podolak, Marek Śmieja, Jacek Tabor, Tomasz Trzciński, Maciej Wołczyk, Bartosz Wójcik
Zero Time Waste: Recycling Predictions in Early Exit Neural Networks, Advances in Neural Information Processing Systems [NeurIPS](MAIN) vol. 34 (2021), 1-13
2.
Karl Aberer, Klaudia Bałazy, Mohammadreza Banaei, Rémi Lebret, Jacek Tabor
Direction is what you need: Improving Word Embedding Compression in Large Language Models, Proceedings of the 6th Workshop On Representation Learning for Nlp (repl4nlp-2021) (2021), 322–330
1.
Klaudia Bałazy, Jacek Tabor, Maciej Wołczyk, Bartosz Wójcik
Finding the Optimal Network Depth in Classification Tasks, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Database (PKDD and ECML combined from 2008) [ECML PKDD], (2020),

Konferencje:

5.
Klaudia Bałazy.
International Conference on Computational Science [ICCS], ICCS 2023, Praga, Republika Czeska, 2023-07-02 - 2023-07-05
4.
Klaudia Bałazy.
European Association of Computational Linguistics [EACL], EACL 2023, Dubrovnik, Chorwacja, 2023-05-01 - 2023-05-07
3.
Klaudia Bałazy.
Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), Neural Information Processing Systems foundation, Virtual, Virtual, 2021-12-06 - 2021-12-14
2.
Klaudia Bałazy.
The 6th Workshop on Representation Learning for NLP (RepL4NLP-2021) , ACL Special Interest Group on Representation Learning (SIGREP), Virtual, Virtual, 2021-08-05 - 2021-08-05
1.
Klaudia Bałazy.
The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021), ACL-IJCNLP'2021, Virtual, Virtual, 2021-08-02 - 2021-08-05