Klaudia Bałazy
6 papers · 2021–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot (5) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (11) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird
🐝
Cross-Pollinator
(14)
Conferences
EACL (2)
ACL (1)
EMNLP (1)
IJCNLP (1)
NIPS (1)
Top co-authors
Keywords
matrix factorization
(3)
model compression
(3)
transformer language model
(2)
word embedding
(2)
model calibration
(1)
early exit
(1)
adversarial attack
(1)
language model
(1)
parameter-efficient fine-tuning
(1)
low-rank adaptation
(1)
adversarial loss
(1)
inference efficiency
(1)
autoencoder architecture
(1)
model efficiency
(1)
gradient-based attack
(1)
inference time
(1)
transformer-based model
(1)
transformer model
(1)
neural network
(1)
embedding compression
(1)
Papers
Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRA
EMNLP 2025
Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks
EACL 2023
Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models
EACL 2023
Zero Time Waste: Recycling Predictions in Early Exit Neural Networks
NIPS 2021
Direction is what you need: Improving Word Embedding Compression in Large Language Models
ACL 2021
Direction is what you need: Improving Word Embedding Compression in Large Language Models
IJCNLP 2021