Simon Kornblith
Artificial Intelligence · 2015–2023
A researcher in the Science corpus: 20 papers; trusts 2,827 researchers and is trusted by 8,488 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 719 citations into it; #389 of 36,961 by trust here, #592 by citations
- Computer Vision and Pattern Recognition — 683 citations into it; #390 of 21,973 by trust here, #494 by citations
- Representation & Self-Supervised Learning — 215 citations into it; #78 of 3,156 by trust here, #61 by citations
- Optimization & Training — 114 citations into it; #916 of 2,605 by trust here, #612 by citations
- Model Architectures — 99 citations into it
- Evaluation & Benchmarks — 95 citations into it; #535 of 3,155 by trust here, #771 by citations
- Safety, Robustness & Interpretability — 84 citations into it
- Generative Models — 63 citations into it
Whom Simon Kornblith trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Alex Krizhevsky
- Geoffrey E. Hinton
- Ross B. Girshick
- Yoshua Bengio
- Diederik P. Kingma
- Christian Szegedy
- Ilya Sutskever
- Karen Simonyan
- Yann LeCun
Who trusts Simon Kornblith overall
- Maithra Raghu
- Quoc V. Le
- Ting-Li Chen
- Yoshua Bengio
- Kaiming He
- Xinlei Chen
- Geoffrey E. Hinton
- Trevor Darrell
- Xiaohua Zhai
- Dacheng Tao
Papers from Simon Kornblith's perspective
Ordered by how strongly the researchers Simon Kornblith trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- 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
- A Simple Framework for Contrastive Learning of Visual Representations (2020) — 25,300 citations
- Big Self-Supervised Models are Strong Semi-Supervised Learners (2020) — 2,576 citations
- Do Better ImageNet Models Transfer Better? (2018) — 1,561 citations
- When Does Label Smoothing Help? (2019) — 2,425 citations
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time (2022) — 1,632 citations
- Similarity of Neural Network Representations Revisited (2019) — 2,348 citations
- Domain Adaptive Transfer Learning with Specialist Models (2018) — 116 citations
- OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models (2023) — 642 citations
- Do Vision Transformers See Like Convolutional Neural Networks? (2021) — 1,440 citations
- Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth (2020) — 340 citations
- Big Self-Supervised Models Advance Medical Image Classification (2021) — 741 citations
- Synthetic Data from Diffusion Models Improves ImageNet Classification (2023) — 451 citations
- Saccader: Improving Accuracy of Hard Attention Models for Vision (2019) — 82 citations
- Towards Generalist Biomedical AI (2023) — 549 citations
- Why Do Better Loss Functions Lead to Less Transferable Features? (2020) — 108 citations
- Subclass Distillation (2020) — 36 citations
- The Origins and Prevalence of Texture Bias in Convolutional Neural Networks (2019) — 356 citations
- Lipschitz Networks and Distributional Robustness (2018) — 12 citations
- Laminar recordings in frontal cortex suggest distinct layers for maintenance and control of working memory (2018)
- Stimulus Load and Oscillatory Activity in Higher Cortex. (2015)