Lijun Wu

Artificial Intelligence · with Liu · 2017–2021

A researcher in the Science corpus: 16 papers; trusts 665 researchers and is trusted by 10 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 405 citations into it; #13,930 of 35,345 by trust here, #3,229 by citations
• Computer Vision and Pattern Recognition — 283 citations into it; #11,278 of 21,575 by trust here, #2,814 by citations
• Natural Language Processing — 282 citations into it; #2,617 of 5,688 by trust here, #891 by citations
• Model Architectures — 94 citations into it; #2,177 of 2,278 by trust here, #1,433 by citations
• Optimization & Training — 69 citations into it
• Evaluation & Benchmarks — 40 citations into it
• Representation & Self-Supervised Learning — 31 citations into it
• Reinforcement Learning — 28 citations into it

Whom Lijun Wu trusts overall

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

1. Diederik P. Kingma
2. Yoshua Bengio
3. Rico Sennrich
4. Ilya Sutskever
5. Geoffrey E. Hinton
6. Kaiming He
7. Alex Krizhevsky
8. Ronald J. Williams
9. Dzmitry Bahdanau
10. Jimmy Ba

Who trusts Lijun Wu overall

1. Yingce Xia
2. Xu Tan
3. Fei Tian
4. Tao Qin
5. Tianxing He
6. Di He
7. Julia Kreutzer
8. Brielen Madureira
9. Tie-Yan Liu
10. Yang Feng

Papers from Lijun Wu's perspective

Ordered by how strongly the researchers Lijun Wu 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. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
10. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)

Their papers

• Achieving Human Parity on Automatic Chinese to English News Translation (2018) — 645 citations
• Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection (2020) — 1,924 citations
• Microsoft Research Asia’s Systems for WMT19 (2019) — 26 citations
• Adversarial Neural Machine Translation (2017) — 137 citations
• R-Drop: Regularized Dropout for Neural Networks (2021) — 568 citations
• A Study of Reinforcement Learning for Neural Machine Translation (2018) — 189 citations
• Depth Growing for Neural Machine Translation (2019) — 45 citations
• Learning to Teach with Dynamic Loss Functions (2018) — 126 citations
• Soft Contextual Data Augmentation for Neural Machine Translation (2019) — 136 citations
• Learning to Reweight with Deep Interactions (2021) — 6 citations
• Incorporating BERT into Neural Machine Translation (2020)
• Efficient Bidirectional Neural Machine Translation (2019) — 5 citations
• Exploiting Monolingual Data at Scale for Neural Machine Translation (2019) — 72 citations
• Machine Translation With Weakly Paired Bilingual Documents (2018)
• Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter (2018) — 56 citations
• Deliberation Networks: Sequence Generation Beyond One-Pass Decoding (2017) — 221 citations