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 about 10 hours ago

openeurollm/EU-Instruct-Synthetic

upvoted a collection 1 day ago

Qwen-AgentWorld

new activity 1 day ago

SBB/ZEFYS2025:Dataset Splits

View all activity

Organizations

upvoted a collection 1 day ago

Qwen-AgentWorld

3 items • Updated 1 day ago • 43

upvoted an article 8 days ago

Article

GLM-5.2: Built for Long-Horizon Tasks

zai-org

•

9 days ago

• 104

upvoted a paper 11 days ago

Small LLMs: Pruning vs. Training from Scratch

Paper • 2606.14150 • Published 14 days ago • 2

upvoted 2 papers 14 days ago

MÖVE: A Holistic LLM Benchmark for the German Public Sector

Paper • 2606.13111 • Published 15 days ago • 2

On Subquadratic Architectures: From Applications to Principles

Paper • 2606.12364 • Published 15 days ago • 23

upvoted a paper 16 days ago

TiME: Tiny Monolingual Encoders for Efficient NLP Pipelines

Paper • 2512.14645 • Published Dec 16, 2025 • 1

upvoted a collection 21 days ago

KletterMix

4 items • Updated 21 days ago • 6

upvoted a paper 22 days ago

KletterMix: Climbing Toward High-Quality German Pretraining Data

Paper • 2606.03773 • Published 23 days ago • 21

upvoted a paper 24 days ago

Bundesrecht: An Open Library and Corpus for German Statutory Reference Processing

Paper • 2605.31338 • Published 28 days ago • 1

upvoted 3 papers 28 days ago

GRUFF: LLM Pronoun Fidelity, Reasoning, and Biases in German

Paper • 2605.30214 • Published 29 days ago • 1

Unlocking the Working Memory of Large Language Models for Latent Reasoning

Paper • 2605.30343 • Published 29 days ago • 1

LLMSurgeon: Diagnosing Data Mixture of Large Language Models

Paper • 2605.30348 • Published 29 days ago • 1

upvoted a collection 29 days ago

RFDetr

RF-DETR checkpoints converted to be used with 🤗 Transformers • 15 items • Updated 29 days ago • 17

upvoted 2 papers about 1 month ago

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

Paper • 2605.22791 • Published May 21 • 33

HRM-Text: Efficient Pretraining Beyond Scaling

Paper • 2605.20613 • Published May 20 • 319

upvoted 3 collections about 1 month ago

Fastest timm models > 75.3% IN-1k Top-1 (Original ResNet-50)

Fastest image classification models with 75.3% accuracy in ImageNet-1k . • 21 items • Updated Sep 19, 2025 • 5

Gliner Guard v1

GLiNER2-based guardrail for PII, content safety classification, prompt attacks detection and more via single forward pass • 5 items • Updated May 9 • 7

Ideology Prediction of German Political Texts

33 items • Updated Sep 15, 2025 • 1

upvoted a paper about 1 month ago

Ideology Prediction of German Political Texts

Paper • 2605.14352 • Published May 14 • 6

upvoted an article about 1 month ago

Article

BidirLM: Turning Generative LLMs into the Best Open-Source Omnimodal Encoders

Nicolas-BZRD

•

Apr 7

• 28