Bayerische Staatsbibliothek

AI & ML interests

(Historical) Named Entity Recognition, LM Pretraining

Recent Activity

stefan-it  submitted a paper 3 days ago

Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling

stefan-it  submitted a paper 3 months ago

FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale

stefan-it  authored a paper 6 months ago

SindBERT, the Sailor: Charting the Seas of Turkish NLP

View all activity

Team members 4