Adam Paszke

Computer Vision and Pattern Recognition · 2016–2025

A researcher in the Science corpus: 6 papers; trusts 219 researchers and is trusted by 135 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 41 citations into it; #3,902 of 21,575 by trust here, #3,558 by citations
• Artificial Intelligence — 34 citations into it; #7,391 of 35,345 by trust here, #545 by citations
• Model Architectures — 19 citations into it; #709 of 2,278 by trust here, #963 by citations
• ML Systems & Hardware — 16 citations into it; #31 of 575 by trust here, #2 by citations
• Optimization & Training — 12 citations into it
• Efficiency & Compression — 8 citations into it
• Computer Networks and Communications — 7 citations into it

Whom Adam Paszke trusts overall

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

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

Who trusts Adam Paszke overall

1. Yoshua Bengio
2. Da-Wei Zhou
3. Zhe Gan
4. Yi Yang
5. Andrew Zisserman
6. Mohit Bansal
7. Timo Schick
8. Ruslan Salakhutdinov
9. Abhinav Kumar Gupta
10. Sebastian Hofstätter

Papers from Adam Paszke's perspective

Ordered by how strongly the researchers Adam Paszke 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. ImageNet Large Scale Visual Recognition Challenge
10. Going deeper with convolutions

Their papers

• PyTorch: An Imperative Style, High-Performance Deep Learning Library (2019) — 53,912 citations
• ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation (2016) — 2,375 citations
• An Analysis of Deep Neural Network Models for Practical Applications (2016) — 1,252 citations
• Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context (2024) — 3,818 citations
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025) — 3,609 citations
• Automatic differentiation in PyTorch (2017) — 16,222 citations