Klaudia Bałazy
5 papers · 2021–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
matrix factorization
(2)
transformer language model
(2)
model compression
(2)
uncertainty quantification
(1)
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)
word embedding
(1)
gradient-based attack
(1)
inference time
(1)
transformer-based model
(1)
transformer model
(1)
neural network
(1)
Papers
Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRA
EMNLP 2025
Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models
EACL 2023
Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks
EACL 2023
Direction is what you need: Improving Word Embedding Compression in Large Language Models
ACL 2021
Zero Time Waste: Recycling Predictions in Early Exit Neural Networks
NeurIPS 2021