Ján Cegin

Publication Activity (10 Years)

Years Active: 2020-2024
Publications (10 Years): 9

Top Topics

Machine Learning

Computational Model

Test Data Generation

Simulated Annealing Algorithm

Top Venues

Publications

Ján Cegin, Branislav Pecher, Jakub Simko, Ivan Srba, Mária Bieliková, Peter Brusilovsky
Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation. ACL (1) (2024)
Branislav Pecher, Ján Cegin, Róbert Belanec, Jakub Simko, Ivan Srba, Mária Bieliková
Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation. CoRR (2024)
Ján Cegin, Branislav Pecher, Jakub Simko, Ivan Srba, Mária Bieliková, Peter Brusilovsky
Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation. CoRR (2024)
Ján Cegin, Jakub Simko, Peter Brusilovsky
ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness. EMNLP (2023)
Ján Cegin, Jakub Simko, Peter Brusilovsky
ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness. CoRR (2023)
Ján Cegin, Jakub Simko, Peter Brusilovsky
A Game for Crowdsourcing Adversarial Examples for False Information Detection. AiOfAi@IJCAI (2022)
Ján Cegin, Karol Rástocný
Test Data Generation for MC/DC Criterion using Reinforcement Learning. ICST Workshops (2020)
Ján Cegin
Machine learning based test data generation for safety-critical software. ESEC/SIGSOFT FSE (2020)
Ján Cegin, Karol Rástocný, Mária Bieliková
Synthesized dataset for search-based test data generation methods focused on MC/DC criterion. QRS Companion (2020)