Victor Sanh
Artificial Intelligence · 2018–2024
A researcher in the Science corpus: 19 papers; trusts 1,457 researchers and is trusted by 858 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 832 citations into it; #1,215 of 36,961 by trust here, #553 by citations
- Natural Language Processing — 435 citations into it; #1,568 of 5,725 by trust here, #1,091 by citations
- Computer Vision and Pattern Recognition — 344 citations into it; #2,859 of 21,973 by trust here, #1,214 by citations
- Large Language Models — 219 citations into it
- Evaluation & Benchmarks — 198 citations into it; #2,214 of 3,155 by trust here, #1,769 by citations
- Efficiency & Compression — 85 citations into it; #53 of 1,273 by trust here, #72 by citations
- Multimodal Learning — 72 citations into it
- Model Architectures — 61 citations into it
Whom Victor Sanh 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
- Yann LeCun
- Oriol Vinyals
- Alex Graves
- Richard Socher
Who trusts Victor Sanh overall
- Sebastian Hofstätter
- Canwen Xu
- Sehoon Kim
- Alexander M. Rush
- Yi Tay
- Yonatan Belinkov
- Kawin Ethayarajh
- Wenhui Wang
- Zi-Mei Yao
- Samira Abnar
Papers from Victor Sanh's perspective
Ordered by how strongly the researchers Victor Sanh 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
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
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
- PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts (2022) — 417 citations
- OBELISC: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents (2023) — 370 citations
- HuggingFace's Transformers: State-of-the-art Natural Language Processing (2019)
- Movement Pruning: Adaptive Sparsity by Fine-Tuning (2020) — 623 citations
- What Language Model to Train if You Have One Million GPU Hours? (2022) — 125 citations
- A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks (2018) — 248 citations
- Datasets: A Community Library for Natural Language Processing (2021) — 775 citations
- Low-Complexity Probing via Finding Subnetworks (2021) — 77 citations
- Block Pruning For Faster Transformers (2021) — 267 citations
- What matters when building vision-language models? (2024) — 379 citations
- Learning from others' mistakes: Avoiding dataset biases without modeling them (2020) — 124 citations
- When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards (2024) — 153 citations
- Multitask Prompted Training Enables Zero-Shot Task Generalization (2022) — 242 citations
- Transformers: State-of-the-Art Natural Language Processing (2020) — 24 citations