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

liked a dataset 3 days ago

openlegaldata/laws-germany

upvoted a paper 3 days ago

Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention

liked a dataset 3 days ago

matybohacek/benchmarking-cultures-25

View all activity

Organizations

New activity in openeurollm/Dolci-Instruct-SFT-translated 4 days ago

More information about translation process

#2 opened 4 days ago by

commented 2 papers 11 days ago

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

Paper • 2604.02045 • Published Apr 2 • 38 •

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

Paper • 2604.02045 • Published Apr 2 • 38 •

commented a paper 12 days ago

A Causal Language Modeling Detour Improves Encoder Continued Pretraining

Paper • 2605.12438 • Published 13 days ago • 7 •

commented a paper 25 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 •

commented a paper about 1 month ago

Decoding Text Spans for Efficient and Accurate Named-Entity Recognition

Paper • 2604.20447 • Published Apr 22 • 2 •

commented 2 papers 2 months ago

Effective Distillation to Hybrid xLSTM Architectures

Paper • 2603.15590 • Published Mar 16 • 33 •

TildeOpen LLM: Leveraging Curriculum Learning to Achieve Equitable Language Representation

Paper • 2603.08182 • Published Mar 9 • 1 •

New activity in stefan-it/Groundsource 2 months ago

Help Addding New Metadata!

#1 opened 2 months ago by

commented 3 papers 3 months ago

Avey-B

Paper • 2602.15814 • Published Feb 17 • 3 •

Avey-B

Paper • 2602.15814 • Published Feb 17 • 3 •

Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning

Paper • 2602.11149 • Published Feb 11 • 18 •

commented a paper 4 months ago

FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale

Paper • 2601.22146 • Published Jan 29 • 12 •

commented a paper 5 months ago

Bolmo: Byteifying the Next Generation of Language Models

Paper • 2512.15586 • Published Dec 17, 2025 • 18 •

commented a paper 6 months ago

Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining

Paper • 2511.21613 • Published Nov 26, 2025 • 2 •

New activity in pdelobelle/baguettotron-nl 6 months ago

Fine-Tuning example

#1 opened 6 months ago by

New activity in enguard/multi-lingual-prompt-moderation 7 months ago

Data Quality

#2 opened 7 months ago by

commented 2 papers 7 months ago

Gaperon: A Peppered English-French Generative Language Model Suite

Paper • 2510.25771 • Published Oct 29, 2025 • 17 •

Mask and You Shall Receive: Optimizing Masked Language Modeling For Pretraining BabyLMs

Paper • 2510.20475 • Published Oct 23, 2025 • 1 •

New activity in nanochat-students/README 7 months ago

🥦 Pretraining Thread

#2 opened 7 months ago by