Klaudia Balazy

According to our database1, Klaudia Balazy authored at least 9 papers between 2020 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters.
CoRR, 2024

2023
Zero time waste in pre-trained early exit neural networks.
Neural Networks, November, 2023

Exploiting Transformer Activation Sparsity with Dynamic Inference.
CoRR, 2023

r-softmax: Generalized Softmax with Controllable Sparsity Rate.
Proceedings of the Computational Science - ICCS 2023, 2023

Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks.
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, 2023

Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models.
Proceedings of the Findings of the Association for Computational Linguistics: EACL 2023, 2023

2021
Direction is what you need: Improving Word Embedding Compression in Large Language Models.
Proceedings of the 6th Workshop on Representation Learning for NLP, 2021

Zero Time Waste: Recycling Predictions in Early Exit Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020
Finding the Optimal Network Depth in Classification Tasks.
Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2020


  Loading...