Publications
- MoxE: Mixture of xLSTM Experts with Entropy-Aware Routing for Efficient Language Modeling
Preprint on arXiv
- Distil-xLSTM: Learning Attention Mechanisms through Recurrent Structures
Preprint on arXiv
- From Apologies to Insights: Extracting Topics from ChatGPT Apologetic Responses
Published in the Journal of Decision Systems
- Assessing Large Language Models Effectiveness in Outdated Method Renaming
Accepted to ICSOC 2024