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

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Andrew M. Dai

Andrew M. Dai

Finetuned Language Models Are Zero-Shot Learners


Sep 03, 2021
Jason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai, Quoc V. Le

Figure 1 for Finetuned Language Models Are Zero-Shot Learners
Figure 2 for Finetuned Language Models Are Zero-Shot Learners
Figure 3 for Finetuned Language Models Are Zero-Shot Learners
Figure 4 for Finetuned Language Models Are Zero-Shot Learners

  Access Paper or Ask Questions

BEDS-Bench: Behavior of EHR-models under Distributional Shift--A Benchmark


Jul 17, 2021
Anand Avati, Martin Seneviratne, Emily Xue, Zhen Xu, Balaji Lakshminarayanan, Andrew M. Dai

Figure 1 for BEDS-Bench: Behavior of EHR-models under Distributional Shift--A Benchmark
Figure 2 for BEDS-Bench: Behavior of EHR-models under Distributional Shift--A Benchmark
Figure 3 for BEDS-Bench: Behavior of EHR-models under Distributional Shift--A Benchmark
Figure 4 for BEDS-Bench: Behavior of EHR-models under Distributional Shift--A Benchmark

  Access Paper or Ask Questions

MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records


Feb 03, 2021
Zhen Xu, David R. So, Andrew M. Dai

Figure 1 for MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records
Figure 2 for MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records
Figure 3 for MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records
Figure 4 for MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records
* Accepted for publication at the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21) 
  Access Paper or Ask Questions

Learnability and Complexity of Quantum Samples


Oct 22, 2020
Murphy Yuezhen Niu, Andrew M. Dai, Li Li, Augustus Odena, Zhengli Zhao, Vadim Smelyanskyi, Hartmut Neven, Sergio Boixo

Figure 1 for Learnability and Complexity of Quantum Samples
Figure 2 for Learnability and Complexity of Quantum Samples
Figure 3 for Learnability and Complexity of Quantum Samples
Figure 4 for Learnability and Complexity of Quantum Samples

  Access Paper or Ask Questions

Training independent subnetworks for robust prediction


Oct 13, 2020
Marton Havasi, Rodolphe Jenatton, Stanislav Fort, Jeremiah Zhe Liu, Jasper Snoek, Balaji Lakshminarayanan, Andrew M. Dai, Dustin Tran

Figure 1 for Training independent subnetworks for robust prediction
Figure 2 for Training independent subnetworks for robust prediction
Figure 3 for Training independent subnetworks for robust prediction
Figure 4 for Training independent subnetworks for robust prediction

  Access Paper or Ask Questions

Learning Unstable Dynamical Systems with Time-Weighted Logarithmic Loss


Jul 10, 2020
Kamil Nar, Yuan Xue, Andrew M. Dai

Figure 1 for Learning Unstable Dynamical Systems with Time-Weighted Logarithmic Loss
Figure 2 for Learning Unstable Dynamical Systems with Time-Weighted Logarithmic Loss
Figure 3 for Learning Unstable Dynamical Systems with Time-Weighted Logarithmic Loss
Figure 4 for Learning Unstable Dynamical Systems with Time-Weighted Logarithmic Loss

  Access Paper or Ask Questions

Flow Contrastive Estimation of Energy-Based Models


Dec 02, 2019
Ruiqi Gao, Erik Nijkamp, Diederik P. Kingma, Zhen Xu, Andrew M. Dai, Ying Nian Wu

Figure 1 for Flow Contrastive Estimation of Energy-Based Models
Figure 2 for Flow Contrastive Estimation of Energy-Based Models
Figure 3 for Flow Contrastive Estimation of Energy-Based Models
Figure 4 for Flow Contrastive Estimation of Energy-Based Models

  Access Paper or Ask Questions

Modelling EHR timeseries by restricting feature interaction


Nov 14, 2019
Kun Zhang, Yuan Xue, Gerardo Flores, Alvin Rajkomar, Claire Cui, Andrew M. Dai

Figure 1 for Modelling EHR timeseries by restricting feature interaction
Figure 2 for Modelling EHR timeseries by restricting feature interaction
* Machine Learning for Health (ML4H) at NeurIPS 2019 - Extended Abstract 
  Access Paper or Ask Questions

Federated and Differentially Private Learning for Electronic Health Records


Nov 13, 2019
Stephen R. Pfohl, Andrew M. Dai, Katherine Heller

Figure 1 for Federated and Differentially Private Learning for Electronic Health Records
Figure 2 for Federated and Differentially Private Learning for Electronic Health Records
* Machine Learning for Health (ML4H) at NeurIPS 2019 - Extended Abstract 
  Access Paper or Ask Questions

Capacity, Bandwidth, and Compositionality in Emergent Language Learning


Oct 24, 2019
Cinjon Resnick, Abhinav Gupta, Jakob Foerster, Andrew M. Dai, Kyunghyun Cho

Figure 1 for Capacity, Bandwidth, and Compositionality in Emergent Language Learning
Figure 2 for Capacity, Bandwidth, and Compositionality in Emergent Language Learning
Figure 3 for Capacity, Bandwidth, and Compositionality in Emergent Language Learning
Figure 4 for Capacity, Bandwidth, and Compositionality in Emergent Language Learning
* The first two authors contributed equally 
  Access Paper or Ask Questions

Improved Patient Classification with Language Model Pretraining Over Clinical Notes


Oct 02, 2019
Jonas Kemp, Alvin Rajkomar, Andrew M. Dai

Figure 1 for Improved Patient Classification with Language Model Pretraining Over Clinical Notes
Figure 2 for Improved Patient Classification with Language Model Pretraining Over Clinical Notes
Figure 3 for Improved Patient Classification with Language Model Pretraining Over Clinical Notes
Figure 4 for Improved Patient Classification with Language Model Pretraining Over Clinical Notes
* Accepted at NeurIPS ML4H 2019, extended abstract track 
  Access Paper or Ask Questions

Learning an Adaptive Learning Rate Schedule


Sep 20, 2019
Zhen Xu, Andrew M. Dai, Jonas Kemp, Luke Metz

Figure 1 for Learning an Adaptive Learning Rate Schedule
Figure 2 for Learning an Adaptive Learning Rate Schedule
Figure 3 for Learning an Adaptive Learning Rate Schedule

  Access Paper or Ask Questions

Graph Convolutional Transformer: Learning the Graphical Structure of Electronic Health Records


Jun 28, 2019
Edward Choi, Zhen Xu, Yujia Li, Michael W. Dusenberry, Gerardo Flores, Yuan Xue, Andrew M. Dai

Figure 1 for Graph Convolutional Transformer: Learning the Graphical Structure of Electronic Health Records
Figure 2 for Graph Convolutional Transformer: Learning the Graphical Structure of Electronic Health Records
Figure 3 for Graph Convolutional Transformer: Learning the Graphical Structure of Electronic Health Records
Figure 4 for Graph Convolutional Transformer: Learning the Graphical Structure of Electronic Health Records

  Access Paper or Ask Questions

Analyzing the Role of Model Uncertainty for Electronic Health Records


Jun 10, 2019
Michael W. Dusenberry, Dustin Tran, Edward Choi, Jonas Kemp, Jeremy Nixon, Ghassen Jerfel, Katherine Heller, Andrew M. Dai

Figure 1 for Analyzing the Role of Model Uncertainty for Electronic Health Records
Figure 2 for Analyzing the Role of Model Uncertainty for Electronic Health Records
Figure 3 for Analyzing the Role of Model Uncertainty for Electronic Health Records
Figure 4 for Analyzing the Role of Model Uncertainty for Electronic Health Records
* Presented at the ICML 2019 Workshop on Uncertainty & Robustness in Deep Learning. Code to be open-sourced 
  Access Paper or Ask Questions

Gmail Smart Compose: Real-Time Assisted Writing


May 17, 2019
Mia Xu Chen, Benjamin N Lee, Gagan Bansal, Yuan Cao, Shuyuan Zhang, Justin Lu, Jackie Tsay, Yinan Wang, Andrew M. Dai, Zhifeng Chen, Timothy Sohn, Yonghui Wu

Figure 1 for Gmail Smart Compose: Real-Time Assisted Writing
Figure 2 for Gmail Smart Compose: Real-Time Assisted Writing
Figure 3 for Gmail Smart Compose: Real-Time Assisted Writing
Figure 4 for Gmail Smart Compose: Real-Time Assisted Writing

  Access Paper or Ask Questions

Music Transformer


Oct 10, 2018
Cheng-Zhi Anna Huang, Ashish Vaswani, Jakob Uszkoreit, Noam Shazeer, Ian Simon, Curtis Hawthorne, Andrew M. Dai, Matthew D. Hoffman, Monica Dinculescu, Douglas Eck

Figure 1 for Music Transformer
Figure 2 for Music Transformer
Figure 3 for Music Transformer
Figure 4 for Music Transformer
* Rewrote many sections to clarify the work, and extended relative attention to the local case. Previous title is "An Improved Relative Self-Attention Mechanism for Transformer with Application to Music Generation" 
  Access Paper or Ask Questions

Peptide-Spectra Matching from Weak Supervision


Aug 22, 2018
Samuel S. Schoenholz, Sean Hackett, Laura Deming, Eugene Melamud, Navdeep Jaitly, Fiona McAllister, Jonathon O'Brien, George Dahl, Bryson Bennett, Andrew M. Dai, Daphne Koller

Figure 1 for Peptide-Spectra Matching from Weak Supervision
Figure 2 for Peptide-Spectra Matching from Weak Supervision
Figure 3 for Peptide-Spectra Matching from Weak Supervision
Figure 4 for Peptide-Spectra Matching from Weak Supervision

  Access Paper or Ask Questions

Learning Longer-term Dependencies in RNNs with Auxiliary Losses


Jun 13, 2018
Trieu H. Trinh, Andrew M. Dai, Minh-Thang Luong, Quoc V. Le

Figure 1 for Learning Longer-term Dependencies in RNNs with Auxiliary Losses
Figure 2 for Learning Longer-term Dependencies in RNNs with Auxiliary Losses
Figure 3 for Learning Longer-term Dependencies in RNNs with Auxiliary Losses
Figure 4 for Learning Longer-term Dependencies in RNNs with Auxiliary Losses
* ICML 2018 
  Access Paper or Ask Questions

Embedding Text in Hyperbolic Spaces


Jun 12, 2018
Bhuwan Dhingra, Christopher J. Shallue, Mohammad Norouzi, Andrew M. Dai, George E. Dahl

Figure 1 for Embedding Text in Hyperbolic Spaces
Figure 2 for Embedding Text in Hyperbolic Spaces
Figure 3 for Embedding Text in Hyperbolic Spaces
Figure 4 for Embedding Text in Hyperbolic Spaces
* TextGraphs 2018 
  Access Paper or Ask Questions

Scalable and accurate deep learning for electronic health records


May 11, 2018
Alvin Rajkomar, Eyal Oren, Kai Chen, Andrew M. Dai, Nissan Hajaj, Peter J. Liu, Xiaobing Liu, Mimi Sun, Patrik Sundberg, Hector Yee, Kun Zhang, Gavin E. Duggan, Gerardo Flores, Michaela Hardt, Jamie Irvine, Quoc Le, Kurt Litsch, Jake Marcus, Alexander Mossin, Justin Tansuwan, De Wang, James Wexler, Jimbo Wilson, Dana Ludwig, Samuel L. Volchenboum, Katherine Chou, Michael Pearson, Srinivasan Madabushi, Nigam H. Shah, Atul J. Butte, Michael Howell, Claire Cui, Greg Corrado, Jeff Dean

Figure 1 for Scalable and accurate deep learning for electronic health records
* npj Digital Medicine 1:18 (2018) 
 * Published version from https://www.nature.com/articles/s41746-018-0029-1 
  Access Paper or Ask Questions

MaskGAN: Better Text Generation via Filling in the______


Mar 01, 2018
William Fedus, Ian Goodfellow, Andrew M. Dai

Figure 1 for MaskGAN: Better Text Generation via Filling in the______
Figure 2 for MaskGAN: Better Text Generation via Filling in the______
Figure 3 for MaskGAN: Better Text Generation via Filling in the______
Figure 4 for MaskGAN: Better Text Generation via Filling in the______
* 16 pages, ICLR 2018 
  Access Paper or Ask Questions

Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step


Feb 20, 2018
William Fedus, Mihaela Rosca, Balaji Lakshminarayanan, Andrew M. Dai, Shakir Mohamed, Ian Goodfellow

Figure 1 for Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
Figure 2 for Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
Figure 3 for Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
Figure 4 for Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
* 18 pages 
  Access Paper or Ask Questions

Who Said What: Modeling Individual Labelers Improves Classification


Jan 04, 2018
Melody Y. Guan, Varun Gulshan, Andrew M. Dai, Geoffrey E. Hinton

Figure 1 for Who Said What: Modeling Individual Labelers Improves Classification
Figure 2 for Who Said What: Modeling Individual Labelers Improves Classification
Figure 3 for Who Said What: Modeling Individual Labelers Improves Classification
Figure 4 for Who Said What: Modeling Individual Labelers Improves Classification
* AAAI 2018 
  Access Paper or Ask Questions

Adversarial Training Methods for Semi-Supervised Text Classification


May 06, 2017
Takeru Miyato, Andrew M. Dai, Ian Goodfellow

Figure 1 for Adversarial Training Methods for Semi-Supervised Text Classification
Figure 2 for Adversarial Training Methods for Semi-Supervised Text Classification
Figure 3 for Adversarial Training Methods for Semi-Supervised Text Classification
Figure 4 for Adversarial Training Methods for Semi-Supervised Text Classification
* Published as a conference paper at ICLR 2017 
  Access Paper or Ask Questions

Generating Sentences from a Continuous Space


May 12, 2016
Samuel R. Bowman, Luke Vilnis, Oriol Vinyals, Andrew M. Dai, Rafal Jozefowicz, Samy Bengio

Figure 1 for Generating Sentences from a Continuous Space
Figure 2 for Generating Sentences from a Continuous Space
Figure 3 for Generating Sentences from a Continuous Space
Figure 4 for Generating Sentences from a Continuous Space
* SIGNLL Conference on Computational Natural Language Learning (CONLL), 2016 
 * First two authors contributed equally. Work was done when all authors were at Google, Inc 
  Access Paper or Ask Questions

Semi-supervised Sequence Learning


Nov 04, 2015
Andrew M. Dai, Quoc V. Le

Figure 1 for Semi-supervised Sequence Learning
Figure 2 for Semi-supervised Sequence Learning
Figure 3 for Semi-supervised Sequence Learning
Figure 4 for Semi-supervised Sequence Learning

  Access Paper or Ask Questions

Document Embedding with Paragraph Vectors


Jul 29, 2015
Andrew M. Dai, Christopher Olah, Quoc V. Le

Figure 1 for Document Embedding with Paragraph Vectors
Figure 2 for Document Embedding with Paragraph Vectors
Figure 3 for Document Embedding with Paragraph Vectors
Figure 4 for Document Embedding with Paragraph Vectors
* 8 pages 
  Access Paper or Ask Questions

The supervised hierarchical Dirichlet process


Dec 17, 2014
Andrew M. Dai, Amos J. Storkey

Figure 1 for The supervised hierarchical Dirichlet process
Figure 2 for The supervised hierarchical Dirichlet process
Figure 3 for The supervised hierarchical Dirichlet process
Figure 4 for The supervised hierarchical Dirichlet process
* 14 pages 
  Access Paper or Ask Questions