Stefan Schweter PRO

stefan-it's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 1 day ago

Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models

Paper • 2505.16538 • Published 3 days ago • 2

upvoted a paper 3 days ago

Tracing Multilingual Factual Knowledge Acquisition in Pretraining

Paper • 2505.14824 • Published 4 days ago • 3

upvoted a paper 4 days ago

Probing BERT for German Compound Semantics

Paper • 2505.14130 • Published 5 days ago • 1

upvoted a collection 4 days ago

Gemma 3n Preview

Collection

2 items • Updated 4 days ago • 64

upvoted a paper 10 days ago

Absolute Zero: Reinforced Self-play Reasoning with Zero Data

Paper • 2505.03335 • Published 19 days ago • 160

upvoted a paper 14 days ago

When Bad Data Leads to Good Models

Paper • 2505.04741 • Published 17 days ago • 1

upvoted a paper 15 days ago

Multilingual k-Nearest-Neighbor Machine Translation

Paper • 2310.14644 • Published Oct 23, 2023 • 2

upvoted an article 15 days ago

view article

Article

XetHub is joining Hugging Face!

By and 1 other •

Aug 8, 2024

• 95

upvoted a paper 16 days ago

ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning

Paper • 2111.10952 • Published Nov 22, 2021 • 2

upvoted a collection 17 days ago

Eynollah models

Collection

Eynollah models for document image processing and layout analysis tasks. • 14 items • Updated Mar 27 • 3

upvoted 2 papers 17 days ago

Large Means Left: Political Bias in Large Language Models Increases with Their Number of Parameters

Paper • 2505.04393 • Published 18 days ago • 1

Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs

Paper • 2505.04519 • Published 17 days ago • 2

upvoted a paper 19 days ago

ReplaceMe: Network Simplification via Layer Pruning and Linear Transformations

Paper • 2505.02819 • Published 19 days ago • 24

upvoted a paper 22 days ago

Aleph-Alpha-GermanWeb: Improving German-language LLM pre-training with model-based data curation and synthetic data generation

Paper • 2505.00022 • Published about 1 month ago • 1

upvoted 2 papers 26 days ago

Efficient Domain-adaptive Continual Pretraining for the Process Industry in the German Language

Paper • 2504.19856 • Published 26 days ago • 1

Even Small Reasoners Should Quote Their Sources: Introducing the Pleias-RAG Model Family

Paper • 2504.18225 • Published 30 days ago • 12

upvoted 3 papers about 1 month ago

A Post-trainer's Guide to Multilingual Training Data: Uncovering Cross-lingual Transfer Dynamics

Paper • 2504.16677 • Published Apr 23 • 1

ModernBERT or DeBERTaV3? Examining Architecture and Data Influence on Transformer Encoder Models Performance

Paper • 2504.08716 • Published Apr 11 • 10

OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

Paper • 2504.07096 • Published Apr 9 • 73

upvoted a paper about 2 months ago

Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation

Paper • 2504.06225 • Published Apr 8 • 1