Stefan Schweter's picture

In a Training Loop 🔄

Stefan Schweter PRO

stefan-it

·

https://schweter.bayern

AI & ML interests

Flair Library 💕, NER & PoS Tagging, LM Pretraining (mostly encoder-only & encoder-decoder), Historical Language Models, German Language Models, Bavarian NLP 🥨, xLSTM

Recent Activity

upvoted a paper 39 minutes ago

Scaling Laws for Cross-Encoder Reranking

published a dataset about 1 hour ago

stefan-it/secret-german-reasoning

updated a dataset about 1 hour ago

stefan-it/secret-german-reasoning

View all activity

Organizations

upvoted a paper 39 minutes ago

Scaling Laws for Cross-Encoder Reranking

Paper • 2603.04816 • Published 25 days ago • 2

upvoted a collection about 1 hour ago

Biomedical datasets & models

8 items • Updated about 1 hour ago • 1

upvoted a collection about 3 hours ago

Key-Value Means

Models featured in the Key-Value Means paper. • 23 items • Updated 1 day ago • 1

upvoted a paper about 3 hours ago

GLiNER-Relex: A Unified Framework for Joint Named Entity Recognition and Relation Extraction

Paper • 2605.10108 • Published 2 days ago • 1

upvoted 2 papers about 4 hours ago

A Causal Language Modeling Detour Improves Encoder Continued Pretraining

Paper • 2605.12438 • Published 1 day ago • 2

Biomed-Enriched: A Biomedical Dataset Enriched with LLMs for Pretraining and Extracting Rare and Hidden Content

Paper • 2506.20331 • Published Jun 25, 2025 • 6

upvoted a collection 4 days ago

Efficient-DLM

2 items • Updated 4 days ago • 2

upvoted a paper 8 days ago

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

Paper • 2604.28075 • Published 13 days ago • 19

upvoted a collection 9 days ago

German LLM Benchmarks

Improved German versions of widely used LLM benchmarks • 4 items • Updated 9 days ago • 1

upvoted an article 11 days ago

Article

Run Gemma 4 on Intel® Arc™ GPUs Out-Of-the-Box

MatrixYao

•

Apr 1

• 9

upvoted a paper 13 days ago

On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models

Paper • 1511.09249 • Published Nov 30, 2015 • 1

upvoted a paper 14 days ago

BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs

Paper • 2604.02045 • Published Apr 2 • 36

upvoted an article 15 days ago

Article

Turkish spaCy models

turkish-nlp-suite

•

15 days ago

• 1

upvoted a paper 19 days ago

Decoding Text Spans for Efficient and Accurate Named-Entity Recognition

Paper • 2604.20447 • Published 21 days ago • 2

upvoted an article 20 days ago

Article

mlinter: a linter for Transformers modeling files

huggingface

•

21 days ago

• 9

upvoted a collection 28 days ago

GlotSuite

GlotSuite: Paving the Way for Bringing Generative AI to Underserved Communities • 17 items • Updated 28 days ago • 3

upvoted an article about 1 month ago

Article

How we OCR'ed 30,000 papers using Codex, open OCR models and Jobs

nielsr

•

Apr 7

• 61

upvoted a collection about 1 month ago

Gemma 4

12 items • Updated 8 days ago • 797

upvoted a collection about 2 months ago

fiNERweb

A multilingual dataset for NER covering 91 langauges and 25 scripts • 3 items • Updated Dec 16, 2025 • 3

upvoted a paper about 2 months ago

F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World

Paper • 2603.19223 • Published Mar 19 • 31