Michalis Vazirgiannis
- Papers
- 13
Cite
Notes
Only stored in your browser.
Authored papers
13YaPO: Learnable Sparse Activation Steering Vectors for Domain Adaptation
arXiv 2026
LLM as a Broken Telephone: Iterative Generation Distorts Information
arXiv 2025
Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVR
arXiv 2025
Fast-Decoding Diffusion Language Models via Progress-Aware Confidence Schedules
arXiv 2025
Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text
arXiv 2025
Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks
arXiv 2024
Prot2Text: Multimodal Protein's Function Generation with GNNs and Transformers
arXiv 2023
The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text
arXiv 2023
GreekBART: The First Pretrained Greek Sequence-to-Sequence Model
arXiv 2023
Path Neural Networks: Expressive and Accurate Graph Neural Networks
arXiv 2023
Abstractive Meeting Summarization: A Survey
arXiv 2022
FrugalScore: Learning Cheaper, Lighter and Faster Evaluation Metricsfor Automatic Text Generation
arXiv 2021
BARThez: a Skilled Pretrained French Sequence-to-Sequence Model
EMNLP 2021 11
Affiliations
Frequent co-authors
10from 13 papers