Justin Gilmer
Artificial Intelligence · 2016–2023
A researcher in the Science corpus: 22 papers; trusts 1,281 researchers and is trusted by 720 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 644 citations into it; #1,618 of 36,961 by trust here, #916 by citations
- Computer Vision and Pattern Recognition — 383 citations into it; #2,686 of 21,973 by trust here, #1,347 by citations
- Safety, Robustness & Interpretability — 250 citations into it; #155 of 2,259 by trust here, #51 by citations
- Model Architectures — 98 citations into it; #688 of 2,288 by trust here, #910 by citations
- Representation & Self-Supervised Learning — 80 citations into it; #1,155 of 3,156 by trust here, #1,431 by citations
- Optimization & Training — 75 citations into it
- Evaluation & Benchmarks — 63 citations into it
- Natural Language Processing — 62 citations into it
Whom Justin Gilmer trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Diederik P. Kingma
- Alex Krizhevsky
- Yoshua Bengio
- Christian Szegedy
- Ilya Sutskever
- Kaiming He
- Yann LeCun
- Ian J. Goodfellow
- Karen Simonyan
Who trusts Justin Gilmer overall
- Yoshua Bengio
- Maithra Raghu
- Sam Schoenholz
- Ekin Dogus Cubuk
- Jörn-Henrik Jacobsen
- Matthias Fey
- Dan Hendrycks
- William L. Hamilton
- Sara Hooker
- Nicholas Carlini
Papers from Justin Gilmer's perspective
Ordered by how strongly the researchers Justin Gilmer 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)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Learning Multiple Layers of Features from Tiny Images
Their papers
- Relational inductive biases, deep learning, and graph networks (2018) — 3,656 citations
- The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization (2020) — 2,442 citations
- Scaling Vision Transformers to 22 Billion Parameters (2023) — 911 citations
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty (2019) — 1,617 citations
- A Fourier Perspective on Model Robustness in Computer Vision (2019) — 638 citations
- Adversarial Spheres (2018) — 358 citations
- Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) (2017) — 2,408 citations
- Sanity Checks for Saliency Maps (2018) — 2,525 citations
- Motivating the Rules of the Game for Adversarial Example Research (2018) — 240 citations
- Adversarial Patch (2017) — 1,317 citations
- Deep Information Propagation (2016) — 429 citations
- Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation (2019) — 229 citations
- Adversarial Examples Are a Natural Consequence of Test Error in Noise (2019) — 343 citations
- SVCCA: Singular Vector Canonical Correlation Analysis for Deep Understanding and Improvement (2017) — 36 citations
- Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values (2018) — 138 citations
- Adaptive Gradient Methods at the Edge of Stability (2022) — 86 citations
- Neural Message Passing for Quantum Chemistry (2017) — 9,235 citations
- Prediction Errors of Molecular Machine Learning Models Lower than Hybrid DFT Error. (2017) — 593 citations
- Machine learning prediction errors better than DFT accuracy (2017) — 36 citations
- Fast machine learning models of electronic and energetic properties consistently reach approximation errors better than DFT accuracy (2017) — 19 citations