Andrej Karpathy
Computer Vision and Pattern Recognition · 2012–2024
A researcher in the Science corpus: 14 papers; trusts 2,291 researchers and is trusted by 19,437 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 381 citations into it; #62 of 21,973 by trust here, #46 by citations
- Artificial Intelligence — 287 citations into it; #192 of 36,961 by trust here, #331 by citations
- Natural Language Processing — 111 citations into it; #94 of 5,725 by trust here, #159 by citations
- Multimodal Learning — 93 citations into it; #2 of 1,215 by trust here, #21 by citations
- Evaluation & Benchmarks — 56 citations into it; #129 of 3,155 by trust here, #20 by citations
- Model Architectures — 54 citations into it
- Representation & Self-Supervised Learning — 51 citations into it; #2,209 of 3,156 by trust here, #2,701 by citations
- Generative Models — 23 citations into it; #295 of 1,963 by trust here, #373 by citations
Whom Andrej Karpathy trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Ilya Sutskever
- Yoshua Bengio
- Ross B. Girshick
- Richard Socher
- Yann LeCun
- Karen Simonyan
- Kaiming He
- Diederik P. Kingma
Who trusts Andrej Karpathy overall
- Zhe Gan
- Qi Wu
- Yi Yang
- Trevor Darrell
- Yoshua Bengio
- Mohit Bansal
- Li Fei-Fei
- Andrew Zisserman
- Chunhua Shen
- Ruslan Salakhutdinov
Papers from Andrej Karpathy's perspective
Ordered by how strongly the researchers Andrej Karpathy trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- ImageNet Large Scale Visual Recognition Challenge (2014) — 43,116 citations
- Deep Visual-Semantic Alignments for Generating Image Descriptions (2014) — 6,086 citations
- Large-Scale Video Classification with Convolutional Neural Networks (2014) — 6,709 citations
- Deep Fragment Embeddings for Bidirectional Image Sentence Mapping (2014) — 980 citations
- Grounded Compositional Semantics for Finding and Describing Images with Sentences (2014) — 904 citations
- DenseCap: Fully Convolutional Localization Networks for Dense Captioning (2015) — 1,244 citations
- PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications (2017) — 1,042 citations
- Visualizing and Understanding Recurrent Networks (2015) — 1,142 citations
- World of Bits: An Open-Domain Platform for Web-Based Agents (2017) — 341 citations
- Object discovery in 3D scenes via shape analysis (2013) — 208 citations
- Emergence of Object-Selective Features in Unsupervised Feature Learning (2012) — 66 citations
- Curriculum Learning for Motor Skills (2012) — 60 citations
- GPT-4o System Card (2024) — 4,622 citations
- Deep Visual-Semantic Alignments for Generating Image Descriptions (2017)