Jungshian Li

Artificial Intelligence · 2016–2022

A researcher in the Science corpus: 3 papers; trusts 41 researchers and is trusted by 11 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 58 citations into it
• Computer Vision and Pattern Recognition — 37 citations into it
• Safety, Robustness & Interpretability — 29 citations into it
• Optimization & Training — 22 citations into it; #1,258 of 2,601 by trust here, #692 by citations
• Generative Models — 12 citations into it
• Probabilistic & Bayesian Methods — 8 citations into it
• Computational Mechanics — 7 citations into it
• Model Architectures — 7 citations into it

Whom Jungshian Li trusts overall

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

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

Who trusts Jungshian Li overall

1. Ahmed Khaled
2. Peter Richtárik
3. Anastasia Koloskova
4. Hanlin Tang
5. Hao Yu
6. Cong Xie
7. Zeyuan Allen-Zhu

Papers from Jungshian Li's perspective

Ordered by how strongly the researchers Jungshian Li 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. ImageNet: A large-scale hierarchical image database
4. Long Short-Term Memory
5. Gradient-based learning applied to document recognition
6. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
7. Learning Multiple Layers of Features from Tiny Images
8. Attention is All you Need (Neural Information Processing Systems)
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers (2019) — 640 citations
• Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions (2022) — 467 citations
• QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding (2016) — 1,728 citations