Yu Sun

Artificial Intelligence · with Weinberger · 2015–2019

A researcher in the Science corpus: 7 papers; trusts 525 researchers and is trusted by 1,425 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 198 citations into it; #754 of 35,345 by trust here, #1,117 by citations
• Computer Vision and Pattern Recognition — 169 citations into it; #1,188 of 21,575 by trust here, #1,533 by citations
• Representation & Self-Supervised Learning — 89 citations into it; #1,049 of 3,145 by trust here, #688 by citations
• Safety, Robustness & Interpretability — 37 citations into it; #226 of 2,251 by trust here, #186 by citations
• Optimization & Training — 36 citations into it; #436 of 2,601 by trust here, #204 by citations
• Model Architectures — 34 citations into it
• Natural Language Processing — 23 citations into it; #1,798 of 5,688 by trust here, #1,546 by citations
• Evaluation & Benchmarks — 16 citations into it; #2,913 of 3,147 by trust here, #2,244 by citations

Whom Yu Sun trusts overall

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

1. Kaiming He
2. Alex Krizhevsky
3. Geoffrey E. Hinton
4. Yoshua Bengio
5. Yann LeCun
6. Ilya Sutskever
7. Christian Szegedy
8. Diederik P. Kingma
9. Ross B. Girshick
10. Sergey Ioffe

Who trusts Yu Sun overall

1. Quoc V. Le
2. Andrew Brock
3. Gao Huang
4. Dan Hendrycks
5. Sergey Levine
6. Yoshua Bengio
7. Christoph Feichtenhofer
8. Zhuang Liu
9. Marvin Zhang
10. Trevor Darrell

Papers from Yu Sun's perspective

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

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. ImageNet: A large-scale hierarchical image database
5. Attention is All you Need (Neural Information Processing Systems)
6. Gradient-based learning applied to document recognition
7. Long Short-Term Memory
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. ImageNet Large Scale Visual Recognition Challenge
10. Learning Multiple Layers of Features from Tiny Images

Their papers

• Deep Networks with Stochastic Depth (2016) — 2,707 citations
• On Calibration of Modern Neural Networks (2017) — 8,827 citations
• An empirical study on evaluation metrics of generative adversarial networks (2018) — 306 citations
• Test-Time Training for Out-of-Distribution Generalization (2019) — 107 citations
• Test-Time Training with Self-Supervision for Generalization under Distribution Shifts (2019) — 1,341 citations
• Supervised Word Mover's Distance (2016) — 195 citations
• From Word Embeddings To Document Distances (2015) — 2,274 citations