Thomas Wolf
Artificial Intelligence · 2009–2025
A researcher in the Science corpus: 29 papers; trusts 1,965 researchers and is trusted by 926 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,284 citations into it; #1,200 of 36,961 by trust here, #534 by citations
- Natural Language Processing — 507 citations into it; #1,125 of 5,725 by trust here, #951 by citations
- Computer Vision and Pattern Recognition — 482 citations into it; #2,617 of 21,973 by trust here, #1,177 by citations
- Large Language Models — 254 citations into it
- Representation & Self-Supervised Learning — 198 citations into it; #2,676 of 3,156 by trust here, #2,185 by citations
- Evaluation & Benchmarks — 191 citations into it; #1,197 of 3,155 by trust here, #1,223 by citations
- Information Systems — 133 citations into it
- Safety, Robustness & Interpretability — 78 citations into it
Whom Thomas Wolf trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Yoshua Bengio
- Diederik P. Kingma
- Alex Krizhevsky
- Ilya Sutskever
- Kaiming He
- Alec Radford
- Yann LeCun
- Alex Graves
- Oriol Vinyals
Who trusts Thomas Wolf overall
- Koustuv Sinha
- Andrea Madotto
- Kurt Shuster
- Minlie Huang
- Stephen Roller
- Jason Aaron Edward Weston
- Samuel Humeau
- Zhaojiang Lin
- Yonatan Belinkov
- Behnam Hedayatnia
Papers from Thomas Wolf's perspective
Ordered by how strongly the researchers Thomas Wolf trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter (2019) — 10,143 citations
- Multitask Prompted Training Enables Zero-Shot Task Generalization (2021) — 2,030 citations
- HuggingFace's Transformers: State-of-the-art Natural Language Processing (2019) — 4,184 citations
- BLOOM: A 176B-Parameter Open-Access Multilingual Language Model (2022) — 2,975 citations
- TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents (2019) — 522 citations
- Transfer Learning in Natural Language Processing (2019) — 625 citations
- The Stack: 3 TB of permissively licensed source code (2022) — 482 citations
- Movement Pruning: Adaptive Sparsity by Fine-Tuning (2020) — 623 citations
- A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks (2018) — 248 citations
- VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning (2021) — 77 citations
- StarCoder: may the source be with you! (2023) — 1,263 citations
- Datasets: A Community Library for Natural Language Processing (2021) — 775 citations
- Scaling Data-Constrained Language Models (2023) — 422 citations
- Large-Scale Transfer Learning for Natural Language Generation (2019) — 93 citations
- Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning (2023) — 272 citations
- Learning from others' mistakes: Avoiding dataset biases without modeling them (2020) — 124 citations
- High-precision nanoscale temperature sensing using single defects in diamond. (2013) — 725 citations
- Electric-field sensing using single diamond spins (2011) — 1,033 citations
- Sensing electric fields using single diamond spins (2011) — 228 citations
- SmolLM2: When Smol Goes Big - Data-Centric Training of a Small Language Model (2025) — 299 citations