JG

Justin Gilmer

0009-0003-4813-7874

cs.LGcs.CVstat.MLcs.AIcs.CLcs.CCcs.NEeess.IVHealth caremath.CO

On Valency

published · living versions

Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)

with Been Kim, Martin Wattenberg, Carrie Cai, James Wexler +2

1 version

W_bg4e778xv1 · current

Preprints & journals

33 papers in the corpus · 2011–2024

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Gemini Team Google: Petko Georgiev, Ving Ian Lei, Ryan Burnell et al.

302 citations

2403.05530v52024arXiv

Gemini: A Family of Highly Capable Multimodal Models

Gemini Team Google: Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac et al.

988 citations

2312.11805v52023arXiv

Order Matters in the Presence of Dataset Imbalance for Multilingual Learning

Dami Choi, Derrick Xin, Hamid Dadkhahi et al.

1 citation

2312.06134v12023arXiv

Small-scale proxies for large-scale Transformer training instabilities

Mitchell Wortsman, Peter J. Liu, Lechao Xiao et al.

5 citations

2309.14322v22023arXiv

Replacing softmax with ReLU in Vision Transformers

Mitchell Wortsman, Jaehoon Lee, Justin Gilmer et al.

11 citations

2309.08586v22023arXiv

Benchmarking Neural Network Training Algorithms

George E. Dahl, Frank Schneider, Zachary Nado et al.

8 citations

2306.07179v22023arXiv

Improving Training Stability for Multitask Ranking Models in Recommender Systems

Jiaxi Tang, Yoel Drori, Daryl Chang et al.

11 citations

2302.09178v22023arXiv

Scaling Vision Transformers to 22 Billion Parameters

Mostafa Dehghani, Josip Djolonga, Basil Mustafa et al.

112 citations

2302.05442v12023arXiv

A mobile-optimized artificial intelligence system for gestational age and fetal malpresentation assessment.

Gomes, Ryan G, Vwalika, Bellington, Lee, Chace et al.

47 citations

362494612024Communications medicine. 2022;2:128

Do Current Multi-Task Optimization Methods in Deep Learning Even Help?

Derrick Xin, Behrooz Ghorbani, Ankush Garg et al.

22 citations

2209.11379v12022arXiv

Adaptive Gradient Methods at the Edge of Stability

Jeremy M. Cohen, Behrooz Ghorbani, Shankar Krishnan et al.

2 citations

2207.14484v22022arXiv

Pre-training helps Bayesian optimization too

Zi Wang, George E. Dahl, Kevin Swersky et al.

2 citations

2207.03084v12022arXiv

AI system for fetal ultrasound in low-resource settings

Ryan G. Gomes, Bellington Vwalika, Chace Lee et al.

3 citations

2203.10139v12022arXiv

Predicting the utility of search spaces for black-box optimization: a simple, budget-aware approach

Setareh Ariafar, Justin Gilmer, Zachary Nado et al.

0 citations

2112.08250v22021arXiv

A Loss Curvature Perspective on Training Instability in Deep Learning

Justin Gilmer, Behrooz Ghorbani, Ankush Garg et al.

6 citations

2110.04369v12021arXiv

Pre-trained Gaussian Processes for Bayesian Optimization

Zi Wang, George E. Dahl, Kevin Swersky et al.

17 citations

2109.08215v62021Journal of Machine Learning Research, 25(212):1-83, 2024. URL http://jmlr.org/papers/v25/23-0269.html

A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes

Zachary Nado, Justin M. Gilmer, Christopher J. Shallue et al.

11 citations

2102.06356v32021arXiv

The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization

Dan Hendrycks, Steven Basart, Norman Mu et al.

1,219 citations

2006.16241v32020arXiv

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

Dan Hendrycks, Norman Mu, Ekin D. Cubuk et al.

783 citations

1912.02781v22019arXiv

A Fourier Perspective on Model Robustness in Computer Vision

Dong Yin, Raphael Gontijo Lopes, Jonathon Shlens et al.

323 citations

1906.08988v32019arXiv

Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation

Raphael Gontijo Lopes, Dong Yin, Ben Poole et al.

138 citations

1906.02611v12019arXiv

MNIST-C: A Robustness Benchmark for Computer Vision

Norman Mu, Justin Gilmer

65 citations

1906.02337v12019arXiv

Adversarial Examples Are a Natural Consequence of Test Error in Noise

Nic Ford, Justin Gilmer, Nicolas Carlini et al.

219 citations

1901.10513v12019arXiv

Sanity Checks for Saliency Maps

Julius Adebayo, Justin Gilmer, Michael Muelly et al.

1,294 citations

1810.03292v32018arXiv

Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values

Julius Adebayo, Justin Gilmer, Ian Goodfellow et al.

83 citations

1810.03307v12018arXiv

Adversarial Spheres

Justin Gilmer, Luke Metz, Fartash Faghri et al.

124 citations

1801.02774v32018arXiv

Adversarial Patch

Tom B. Brown, Dandelion Man'e, Aurko Roy et al.

508 citations

1712.09665v22017arXiv

Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)

Been Kim, Martin Wattenberg, Justin Gilmer et al.

1,239 citations

1711.11279v52017ICML 2018

SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability

Maithra Raghu, Justin Gilmer, Jason Yosinski et al.

335 citations

1706.05806v22017arXiv

Neural Message Passing for Quantum Chemistry

Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley et al.

5,064 citations

1704.01212v22017arXiv

Input Switched Affine Networks: An RNN Architecture Designed for Interpretability

Jakob N. Foerster, Justin Gilmer, Jan Chorowski et al.

26 citations

1611.09434v22016arXiv

A communication game related to the sensitivity conjecture

Justin Gilmer, Michal Kouck'y, Michael Saks

1 citation

1511.07729v12015arXiv

On the Density of Happy Numbers

Justin Gilmer

5 citations

1110.3836v42011INTEGERS, 13:2, 2013

Career total: 40 works. 33 are in this corpus.

Profile built from the corpus for this byline.

40

works

13.1K

citations

24

h-index

Corpus papers per year

Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.