Wei Li

Artificial Intelligence · with Matena · 2019–2021

A researcher in the Science corpus: 2 papers; trusts 74 researchers and is trusted by 982 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 149 citations into it; #803 of 35,345 by trust here, #328 by citations
• Natural Language Processing — 108 citations into it; #396 of 5,688 by trust here, #93 by citations
• Computer Vision and Pattern Recognition — 81 citations into it; #1,544 of 21,575 by trust here, #266 by citations
• Model Architectures — 39 citations into it
• Evaluation & Benchmarks — 28 citations into it
• Optimization & Training — 25 citations into it
• Representation & Self-Supervised Learning — 23 citations into it
• Generative Models — 6 citations into it

Whom Wei Li trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Geoffrey E. Hinton
2. Alex Krizhevsky
3. Yoshua Bengio
4. Diederik P. Kingma
5. Ilya Sutskever
6. Alex Graves
7. Kaiming He
8. Yann LeCun
9. Noam Shazeer
10. Tomas Mikolov

Who trusts Wei Li overall

1. Yi Tay
2. Timo Schick
3. Mohit Bansal
4. Thomas Scialom
5. Ronghang Hu
6. Mostafa Dehghani
7. Daniel Khashabi
8. Hinrich Schütze
9. Gautier Izacard
10. Wenhu Chen

Papers from Wei Li's perspective

Ordered by how strongly the researchers Wei Li trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. Attention is All you Need (Neural Information Processing Systems)
3. Long Short-Term Memory
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
5. ImageNet classification with deep convolutional neural networks
6. ImageNet: A large-scale hierarchical image database
7. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
8. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
9. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (2019) — 26,606 citations
• Do Transformer Modifications Transfer Across Implementations and Applications? (2021) — 138 citations