Kang Liu

Artificial Intelligence · with Dolan-Gavitt · 2018–2019

A researcher in the Science corpus: 2 papers; trusts 123 researchers and is trusted by 32 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 52 citations into it; #6,825 of 35,345 by trust here, #9,170 by citations
• Safety, Robustness & Interpretability — 36 citations into it; #663 of 2,251 by trust here, #984 by citations
• Computer Vision and Pattern Recognition — 30 citations into it
• Signal Processing — 26 citations into it; #1,086 of 7,572 by trust here, #1,120 by citations
• Computer Networks and Communications — 13 citations into it
• Information Systems — 9 citations into it
• Efficiency & Compression — 5 citations into it
• Model Architectures — 5 citations into it

Whom Kang Liu trusts overall

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

1. Alex Krizhevsky
2. Geoffrey E. Hinton
3. Ilya Sutskever
4. Yoshua Bengio
5. Kaiming He
6. Yann LeCun
7. Shaoqing Ren
8. Christian Szegedy
9. Alex Graves
10. Diederik P. Kingma

Who trusts Kang Liu overall

1. Eugene Bagdasarian
2. Dongxian Wu
3. Yige Li
4. Yuanshun Yao
5. Yiming Li
6. Baoyuan Wu
7. Yuezun Li
8. Khoa D Doan
9. Alexander Turner
10. Brandon Tran

Papers from Kang Liu's perspective

Ordered by how strongly the researchers Kang Liu 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. Gradient-based learning applied to document recognition
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Attention is All you Need (Neural Information Processing Systems)
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Learning Multiple Layers of Features from Tiny Images
10. Going deeper with convolutions

Their papers

• Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks (2018) — 1,338 citations
• BadNets: Evaluating Backdooring Attacks on Deep Neural Networks (2019) — 1,380 citations