Liyuan Liu

Artificial Intelligence · 2017–2020

A researcher in the Science corpus: 5 papers; trusts 133 researchers and is trusted by 12 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 112 citations into it; #13,688 of 35,345 by trust here, #4,577 by citations
• Computer Vision and Pattern Recognition — 60 citations into it; #12,068 of 21,575 by trust here, #4,926 by citations
• Natural Language Processing — 55 citations into it; #3,903 of 5,688 by trust here, #3,235 by citations
• Model Architectures — 40 citations into it
• Optimization & Training — 39 citations into it; #1,752 of 2,601 by trust here, #538 by citations
• Evaluation & Benchmarks — 13 citations into it
• Representation & Self-Supervised Learning — 10 citations into it; #2,295 of 3,145 by trust here, #2,148 by citations
• Management Science and Operations Research — 6 citations into it

Whom Liyuan Liu trusts overall

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

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

Who trusts Liyuan Liu overall

1. Jeremy Howard
2. Xiaodong Liu
3. M. V. Koroteev
4. Jing Li
5. Li Luo
6. Jie Yang
7. Luckeciano Carvalho Melo
8. Huiyu Wang
9. Yi-Chiao Wu
10. Sebastian Ruder

Papers from Liyuan Liu's perspective

Ordered by how strongly the researchers Liyuan Liu 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. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (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. Learning Multiple Layers of Features from Tiny Images

Their papers

• On the Variance of the Adaptive Learning Rate and Beyond (2019) — 2,272 citations
• Understanding the Difficulty of Training Transformers (2020) — 315 citations
• Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling (2018) — 46 citations
• Empower Sequence Labeling with Task-Aware Neural Language Model (2017) — 354 citations
• On the Transformer Growth for Progressive BERT Training (2020) — 61 citations