Stefan Schweter's picture

Stefan Schweter PRO

stefan-it

·

AI & ML interests

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

Recent Activity

liked a Space 2 days ago

CATIE-AQ/FAT5-report

updated a collection 3 days ago

🇹🇷 Turkish Language Models

reacted to clem's post with 🔥 4 days ago

Nice new space to see how fast your personal or organization followers are growing on HF: https://huggingface.co/spaces/julien-c/follow-history As you can see, I still have more followers than @julien-c even if he's trying to change this by building such cool spaces 😝😝😝

View all activity

Organizations

stefan-it's activity

upvoted an article 4 days ago

Article

Xet is on the Hub

6 days ago

• 31

upvoted 3 papers 5 days ago

xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference

Paper • 2503.13427 • Published 6 days ago • 3

UniBERTs: Adversarial Training for Language-Universal Representations

Paper • 2503.12608 • Published 7 days ago • 1

SuperBPE: Space Travel for Language Models

Paper • 2503.13423 • Published 6 days ago • 6

upvoted a paper 6 days ago

Do Construction Distributions Shape Formal Language Learning In German BabyLMs?

Paper • 2503.11593 • Published 9 days ago • 2

upvoted 2 papers 9 days ago

HyperZcdotZcdotW Operator Connects Slow-Fast Networks for Full Context Interaction

Paper • 2401.17948 • Published Jan 31, 2024 • 4

Transformers without Normalization

Paper • 2503.10622 • Published 10 days ago • 130

upvoted a paper 11 days ago

Modern Models, Medieval Texts: A POS Tagging Study of Old Occitan

Paper • 2503.07827 • Published 13 days ago • 1

upvoted a paper 26 days ago

Reading the unreadable: Creating a dataset of 19th century English newspapers using image-to-text language models

Paper • 2502.14901 • Published Feb 18 • 1

upvoted a paper about 1 month ago

NER4all or Context is All You Need: Using LLMs for low-effort, high-performance NER on historical texts. A humanities informed approach

Paper • 2502.04351 • Published Feb 4 • 1

upvoted 6 papers about 2 months ago

AI-assisted German Employment Contract Review: A Benchmark Dataset

Paper • 2501.17194 • Published Jan 27 • 1

Familiarity: Better Evaluation of Zero-Shot Named Entity Recognition by Quantifying Label Shifts in Synthetic Training Data

Paper • 2412.10121 • Published Dec 13, 2024 • 2

MorphBPE: A Morpho-Aware Tokenizer Bridging Linguistic Complexity for Efficient LLM Training Across Morphologies

Paper • 2502.00894 • Published Feb 2 • 2

PixelWorld: Towards Perceiving Everything as Pixels

Paper • 2501.19339 • Published Jan 31 • 17

Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Experimental Setups Matter

Paper • 2501.14491 • Published Jan 24 • 1

Humanity's Last Exam

Paper • 2501.14249 • Published Jan 24 • 68

upvoted 3 papers 2 months ago

Hierarchical Autoregressive Transformers: Combining Byte-~and Word-Level Processing for Robust, Adaptable Language Models

Paper • 2501.10322 • Published Jan 17 • 1

Towards Best Practices for Open Datasets for LLM Training

Paper • 2501.08365 • Published Jan 14 • 56

AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages

Paper • 2501.08284 • Published Jan 14 • 6