Thomas Wolf
Co-founder and Chief Science Officer of Hugging Face; principal architect of the Transformers and Datasets libraries and initiator of BigScience.
- Role
- chief-science-officer
- Currently at
- Hugging Face
- twitter.com/Thom_Wolf
- GitHub
- github.com/thomwolf
- Scholar
- scholar.google.com/citations
- Papers
- 12
Cite
Notes
Only stored in your browser.
Authored papers
12SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
arXiv 2025
SmolVLM: Redefining small and efficient multimodal models
arXiv 2025
FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language
arXiv 2025
Robot Learning: A Tutorial
arXiv 2025
YourBench: Easy Custom Evaluation Sets for Everyone
arXiv 2025
GAIA: A Benchmark for General AI Assistants
ICLR
Scaling Data-Constrained Language Models
scaling-data-constrained-language-models
Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning
arXiv 2023
Evaluate & Evaluation on the Hub: Better Best Practices for Data and Model Measurements
arXiv 2022
Datasets: A Community Library for Natural Language Processing
EMNLP (ACL) 2021 11
Movement Pruning: Adaptive Sparsity by Fine-Tuning
NeurIPS 2020 12
TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation
arXiv 2020
Eval contributions
1Affiliations
Frequent co-authors
10from 12 papers
Alexander M. Rush
Leandro von Werra
Lewis Tunstall
engineer
Abhishek Thakur
Adil Zouitine
Aleksandra Piktus
Andres Marafioti
Caroline Pascal
Clémentine Fourrier
researcher
Colin Raffel