Pierre Stock

Artificial Intelligence · 2017–2023

A researcher in the Science corpus: 8 papers; trusts 789 researchers and is trusted by 34 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 298 citations into it; #5,474 of 35,345 by trust here, #6,157 by citations
• Computer Vision and Pattern Recognition — 242 citations into it; #7,119 of 21,575 by trust here, #4,584 by citations
• Efficiency & Compression — 115 citations into it; #1,191 of 1,264 by trust here, #731 by citations
• Model Architectures — 92 citations into it
• Large Language Models — 46 citations into it
• Natural Language Processing — 43 citations into it
• Optimization & Training — 43 citations into it
• Safety, Robustness & Interpretability — 42 citations into it; #414 of 2,251 by trust here, #889 by citations

Whom Pierre Stock trusts overall

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

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

Who trusts Pierre Stock overall

1. Nicolas Papernot
2. Nicholas Carlini
3. Giulia Vilone
4. Angelina Wang
5. Chris Dulhanty
6. Shruti Bhargava
7. Angela Fan
8. Patrick Drew McDaniel
9. Ú. Erlingsson
10. Hugo Touvron

Papers from Pierre Stock's perspective

Ordered by how strongly the researchers Pierre Stock 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. ImageNet: A large-scale hierarchical image database
6. Long Short-Term Memory
7. Gradient-based learning applied to document recognition
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

• LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference (2021) — 1,047 citations
• ConvNets and ImageNet Beyond Accuracy: Explanations, Bias Detection, Adversarial Examples and Model Criticism (2017) — 48 citations
• ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases (2017) — 180 citations
• Training with Quantization Noise for Extreme Model Compression (2020) — 267 citations
• TAN without a burn: Scaling Laws of DP-SGD (2022) — 62 citations
• And the Bit Goes Down: Revisiting the Quantization of Neural Networks (2019) — 158 citations
• LLM-QAT: Data-Free Quantization Aware Training for Large Language Models (2023) — 398 citations
• Training with Quantization Noise for Extreme Fixed-Point Compression (2020) — 21 citations