Zhao Song

Artificial Intelligence · with Chen · 2021–2023

A researcher in the Science corpus: 4 papers; trusts 119 researchers and is trusted by 2 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 189 citations into it; #31,599 of 35,345 by trust here, #17,412 by citations
• Computer Vision and Pattern Recognition — 124 citations into it; #19,428 of 21,575 by trust here, #14,151 by citations
• Efficiency & Compression — 85 citations into it
• Model Architectures — 68 citations into it
• Large Language Models — 52 citations into it
• Natural Language Processing — 38 citations into it
• Scaling & Learning Theory — 21 citations into it
• Computational Mechanics — 17 citations into it

Whom Zhao Song trusts overall

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

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

Who trusts Zhao Song overall

1. Tri Dao

Papers from Zhao Song's perspective

Ordered by how strongly the researchers Zhao Song 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. Attention is All you Need (Neural Information Processing Systems)
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Gradient-based learning applied to document recognition
8. ImageNet Large Scale Visual Recognition Challenge
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

• Scatterbrain: Unifying Sparse and Low-rank Attention Approximation (2021) — 175 citations
• Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models (2021) — 95 citations
• Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time (2023) — 356 citations
• H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models (2023) — 817 citations