Search

Abdoul Majid O. Thiombiano

Distil-xLSTM: learning attention mechanisms through recurrent structures
From apologies to insights: extracting topics from ChatGPT apologetic responses
MoxE: mixture of xLSTM experts with entropy-aware routing for efficient language modeling
Assessing large language models effectiveness in outdated method renaming

Published with Wowchemy — the free, open source website builder that empowers creators.