Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for James Zou

James Zou

Did the Model Change? Efficiently Assessing Machine Learning API Shifts

Jul 29, 2021
Lingjiao Chen, Tracy Cai, Matei Zaharia, James Zou

Figure 1 for Did the Model Change? Efficiently Assessing Machine Learning API Shifts

Figure 2 for Did the Model Change? Efficiently Assessing Machine Learning API Shifts

Figure 3 for Did the Model Change? Efficiently Assessing Machine Learning API Shifts

Figure 4 for Did the Model Change? Efficiently Assessing Machine Learning API Shifts

Access Paper or Ask Questions

Do Humans Trust Advice More if it Comes from AI? An Analysis of Human-AI Interactions

Jul 14, 2021
Kailas Vodrahalli, Tobias Gerstenberg, James Zou

Figure 1 for Do Humans Trust Advice More if it Comes from AI? An Analysis of Human-AI Interactions

Figure 2 for Do Humans Trust Advice More if it Comes from AI? An Analysis of Human-AI Interactions

Figure 3 for Do Humans Trust Advice More if it Comes from AI? An Analysis of Human-AI Interactions

Figure 4 for Do Humans Trust Advice More if it Comes from AI? An Analysis of Human-AI Interactions

* 34 pages, 6 figures + 18 full page figures

Access Paper or Ask Questions

Meaningfully Explaining a Model's Mistakes

Jun 24, 2021
Abubakar Abid, James Zou

Figure 1 for Meaningfully Explaining a Model's Mistakes

Figure 2 for Meaningfully Explaining a Model's Mistakes

* ICML workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI

Access Paper or Ask Questions

Group-Structured Adversarial Training

Jun 18, 2021
Farzan Farnia, Amirali Aghazadeh, James Zou, David Tse

Figure 1 for Group-Structured Adversarial Training

Figure 2 for Group-Structured Adversarial Training

Figure 3 for Group-Structured Adversarial Training

Figure 4 for Group-Structured Adversarial Training

Access Paper or Ask Questions

Adversarial Training Helps Transfer Learning via Better Representations

Jun 18, 2021
Zhun Deng, Linjun Zhang, Kailas Vodrahalli, Kenji Kawaguchi, James Zou

Figure 1 for Adversarial Training Helps Transfer Learning via Better Representations

Figure 2 for Adversarial Training Helps Transfer Learning via Better Representations

Figure 3 for Adversarial Training Helps Transfer Learning via Better Representations

Figure 4 for Adversarial Training Helps Transfer Learning via Better Representations

Access Paper or Ask Questions

MLDemon: Deployment Monitoring for Machine Learning Systems

May 05, 2021
Antonio Ginart, Martin Zhang, James Zou

Figure 1 for MLDemon: Deployment Monitoring for Machine Learning Systems

Figure 2 for MLDemon: Deployment Monitoring for Machine Learning Systems

Figure 3 for MLDemon: Deployment Monitoring for Machine Learning Systems

Figure 4 for MLDemon: Deployment Monitoring for Machine Learning Systems

Access Paper or Ask Questions

Data Shapley Valuation for Efficient Batch Active Learning

Apr 16, 2021
Amirata Ghorbani, James Zou, Andre Esteva

Figure 1 for Data Shapley Valuation for Efficient Batch Active Learning

Figure 2 for Data Shapley Valuation for Efficient Batch Active Learning

Figure 3 for Data Shapley Valuation for Efficient Batch Active Learning

Figure 4 for Data Shapley Valuation for Efficient Batch Active Learning

Access Paper or Ask Questions

FrugalMCT: Efficient Online ML API Selection for Multi-Label Classification Tasks

Feb 18, 2021
Lingjiao Chen, Matei Zaharia, James Zou

Figure 1 for FrugalMCT: Efficient Online ML API Selection for Multi-Label Classification Tasks

Figure 2 for FrugalMCT: Efficient Online ML API Selection for Multi-Label Classification Tasks

Figure 3 for FrugalMCT: Efficient Online ML API Selection for Multi-Label Classification Tasks

Figure 4 for FrugalMCT: Efficient Online ML API Selection for Multi-Label Classification Tasks

Access Paper or Ask Questions

How to Learn when Data Reacts to Your Model: Performative Gradient Descent

Feb 16, 2021
Zachary Izzo, Lexing Ying, James Zou

Figure 1 for How to Learn when Data Reacts to Your Model: Performative Gradient Descent

Figure 2 for How to Learn when Data Reacts to Your Model: Performative Gradient Descent

Figure 3 for How to Learn when Data Reacts to Your Model: Performative Gradient Descent

Figure 4 for How to Learn when Data Reacts to Your Model: Performative Gradient Descent

* 21 pages, 5 figures

Access Paper or Ask Questions

When and How Mixup Improves Calibration

Feb 11, 2021
Linjun Zhang, Zhun Deng, Kenji Kawaguchi, James Zou

Figure 1 for When and How Mixup Improves Calibration

Figure 2 for When and How Mixup Improves Calibration

Figure 3 for When and How Mixup Improves Calibration

Figure 4 for When and How Mixup Improves Calibration

Access Paper or Ask Questions

Persistent Anti-Muslim Bias in Large Language Models

Jan 18, 2021
Abubakar Abid, Maheen Farooqi, James Zou

Figure 1 for Persistent Anti-Muslim Bias in Large Language Models

Figure 2 for Persistent Anti-Muslim Bias in Large Language Models

Figure 3 for Persistent Anti-Muslim Bias in Large Language Models

Figure 4 for Persistent Anti-Muslim Bias in Large Language Models

Access Paper or Ask Questions

Neural Group Testing to Accelerate Deep Learning

Nov 21, 2020
Weixin Liang, James Zou

Figure 1 for Neural Group Testing to Accelerate Deep Learning

Figure 2 for Neural Group Testing to Accelerate Deep Learning

Figure 3 for Neural Group Testing to Accelerate Deep Learning

Figure 4 for Neural Group Testing to Accelerate Deep Learning

Access Paper or Ask Questions

How Does Mixup Help With Robustness and Generalization?

Oct 09, 2020
Linjun Zhang, Zhun Deng, Kenji Kawaguchi, Amirata Ghorbani, James Zou

Figure 1 for How Does Mixup Help With Robustness and Generalization?

Figure 2 for How Does Mixup Help With Robustness and Generalization?

Figure 3 for How Does Mixup Help With Robustness and Generalization?

Figure 4 for How Does Mixup Help With Robustness and Generalization?

Access Paper or Ask Questions

Competing AI: How competition feedback affects machine learning

Oct 02, 2020
Antonio Ginart, Eva Zhang, Yongchan Kwon, James Zou

Figure 1 for Competing AI: How competition feedback affects machine learning

Figure 2 for Competing AI: How competition feedback affects machine learning

Figure 3 for Competing AI: How competition feedback affects machine learning

Figure 4 for Competing AI: How competition feedback affects machine learning

* Manuscript

Access Paper or Ask Questions

TrueImage: A Machine Learning Algorithm to Improve the Quality of Telehealth Photos

Oct 01, 2020
Kailas Vodrahalli, Roxana Daneshjou, Roberto A Novoa, Albert Chiou, Justin M Ko, James Zou

Figure 1 for TrueImage: A Machine Learning Algorithm to Improve the Quality of Telehealth Photos

Figure 2 for TrueImage: A Machine Learning Algorithm to Improve the Quality of Telehealth Photos

Figure 3 for TrueImage: A Machine Learning Algorithm to Improve the Quality of Telehealth Photos

Figure 4 for TrueImage: A Machine Learning Algorithm to Improve the Quality of Telehealth Photos

* 12 pages, 5 figures, Preprint of an article published in Pacific Symposium on Biocomputing \c{opyright} 2020 World Scientific Publishing Co., Singapore, http://psb.stanford.edu/

Access Paper or Ask Questions

ALICE: Active Learning with Contrastive Natural Language Explanations

Sep 22, 2020
Weixin Liang, James Zou, Zhou Yu

Figure 1 for ALICE: Active Learning with Contrastive Natural Language Explanations

Figure 2 for ALICE: Active Learning with Contrastive Natural Language Explanations

Figure 3 for ALICE: Active Learning with Contrastive Natural Language Explanations

Figure 4 for ALICE: Active Learning with Contrastive Natural Language Explanations

* EMNLP 2020

Access Paper or Ask Questions

Efficient computation and analysis of distributional Shapley values

Jul 02, 2020
Yongchan Kwon, Manuel A. Rivas, James Zou

Figure 1 for Efficient computation and analysis of distributional Shapley values

Figure 2 for Efficient computation and analysis of distributional Shapley values

Figure 3 for Efficient computation and analysis of distributional Shapley values

Figure 4 for Efficient computation and analysis of distributional Shapley values

* 23 pages

Access Paper or Ask Questions

Improving Adversarial Robustness via Unlabeled Out-of-Domain Data

Jun 15, 2020
Zhun Deng, Linjun Zhang, Amirata Ghorbani, James Zou

Figure 1 for Improving Adversarial Robustness via Unlabeled Out-of-Domain Data

Figure 2 for Improving Adversarial Robustness via Unlabeled Out-of-Domain Data

Figure 3 for Improving Adversarial Robustness via Unlabeled Out-of-Domain Data

Figure 4 for Improving Adversarial Robustness via Unlabeled Out-of-Domain Data

Access Paper or Ask Questions

FrugalML: How to Use ML Prediction APIs More Accurately and Cheaply

Jun 12, 2020
Lingjiao Chen, Matei Zaharia, James Zou

Figure 1 for FrugalML: How to Use ML Prediction APIs More Accurately and Cheaply

Figure 2 for FrugalML: How to Use ML Prediction APIs More Accurately and Cheaply

Figure 3 for FrugalML: How to Use ML Prediction APIs More Accurately and Cheaply

Figure 4 for FrugalML: How to Use ML Prediction APIs More Accurately and Cheaply

Access Paper or Ask Questions

Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation

Jun 12, 2020
Weixin Liang, James Zou, Zhou Yu

Figure 1 for Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation

Figure 2 for Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation

Figure 3 for Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation

Figure 4 for Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation

* ACL 2020

Access Paper or Ask Questions

MOPO: Model-based Offline Policy Optimization

May 27, 2020
Tianhe Yu, Garrett Thomas, Lantao Yu, Stefano Ermon, James Zou, Sergey Levine, Chelsea Finn, Tengyu Ma

Figure 1 for MOPO: Model-based Offline Policy Optimization

Figure 2 for MOPO: Model-based Offline Policy Optimization

Figure 3 for MOPO: Model-based Offline Policy Optimization

Figure 4 for MOPO: Model-based Offline Policy Optimization

* First two authors contributed equally. Last two authors advised equally

Access Paper or Ask Questions

Improving Training on Noisy Stuctured Labels

Mar 08, 2020
Abubakar Abid, James Zou

Figure 1 for Improving Training on Noisy Stuctured Labels

Figure 2 for Improving Training on Noisy Stuctured Labels

Figure 3 for Improving Training on Noisy Stuctured Labels

Figure 4 for Improving Training on Noisy Stuctured Labels

* 8 pages main text, 13 pages total

Access Paper or Ask Questions

A Distributional Framework for Data Valuation

Feb 27, 2020
Amirata Ghorbani, Michael P. Kim, James Zou

Figure 1 for A Distributional Framework for Data Valuation

Figure 2 for A Distributional Framework for Data Valuation

Figure 3 for A Distributional Framework for Data Valuation

Access Paper or Ask Questions

Neuron Shapley: Discovering the Responsible Neurons

Feb 25, 2020
Amirata Ghorbani, James Zou

Figure 1 for Neuron Shapley: Discovering the Responsible Neurons

Figure 2 for Neuron Shapley: Discovering the Responsible Neurons

Figure 3 for Neuron Shapley: Discovering the Responsible Neurons

Figure 4 for Neuron Shapley: Discovering the Responsible Neurons

Access Paper or Ask Questions

Approximate Data Deletion from Machine Learning Models: Algorithms and Evaluations

Feb 24, 2020
Zachary Izzo, Mary Anne Smart, Kamalika Chaudhuri, James Zou

Figure 1 for Approximate Data Deletion from Machine Learning Models: Algorithms and Evaluations

Figure 2 for Approximate Data Deletion from Machine Learning Models: Algorithms and Evaluations

Figure 3 for Approximate Data Deletion from Machine Learning Models: Algorithms and Evaluations

Figure 4 for Approximate Data Deletion from Machine Learning Models: Algorithms and Evaluations

* 20 pages, 2 figures, under review by ICML

Access Paper or Ask Questions