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 Charles Sutton

Charles Sutton

Program Synthesis with Large Language Models


Aug 16, 2021
Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, Charles Sutton

Figure 1 for Program Synthesis with Large Language Models
Figure 2 for Program Synthesis with Large Language Models
Figure 3 for Program Synthesis with Large Language Models
Figure 4 for Program Synthesis with Large Language Models
* Jacob and Augustus contributed equally 
  Access Paper or Ask Questions

SpreadsheetCoder: Formula Prediction from Semi-structured Context


Jun 26, 2021
Xinyun Chen, Petros Maniatis, Rishabh Singh, Charles Sutton, Hanjun Dai, Max Lin, Denny Zhou

Figure 1 for SpreadsheetCoder: Formula Prediction from Semi-structured Context
Figure 2 for SpreadsheetCoder: Formula Prediction from Semi-structured Context
Figure 3 for SpreadsheetCoder: Formula Prediction from Semi-structured Context
Figure 4 for SpreadsheetCoder: Formula Prediction from Semi-structured Context
* Published in ICML 2021 
  Access Paper or Ask Questions

Latent Programmer: Discrete Latent Codes for Program Synthesis


Dec 01, 2020
Joey Hong, David Dohan, Rishabh Singh, Charles Sutton, Manzil Zaheer

Figure 1 for Latent Programmer: Discrete Latent Codes for Program Synthesis
Figure 2 for Latent Programmer: Discrete Latent Codes for Program Synthesis
Figure 3 for Latent Programmer: Discrete Latent Codes for Program Synthesis
Figure 4 for Latent Programmer: Discrete Latent Codes for Program Synthesis
* 15 pages, 9 figures 
  Access Paper or Ask Questions

Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration


Nov 10, 2020
Hanjun Dai, Rishabh Singh, Bo Dai, Charles Sutton, Dale Schuurmans

Figure 1 for Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration
Figure 2 for Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration
Figure 3 for Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration
Figure 4 for Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration
* NeurIPS 2020 
  Access Paper or Ask Questions

Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks


Oct 23, 2020
David Bieber, Charles Sutton, Hugo Larochelle, Daniel Tarlow

Figure 1 for Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks
Figure 2 for Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks
Figure 3 for Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks
Figure 4 for Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks
* Accepted at NeurIPS 2020 
  Access Paper or Ask Questions

Conditional independence by typing


Oct 22, 2020
Maria I. Gorinova, Andrew D. Gordon, Charles Sutton, Matthijs Vakar

Figure 1 for Conditional independence by typing
Figure 2 for Conditional independence by typing
Figure 3 for Conditional independence by typing
Figure 4 for Conditional independence by typing

  Access Paper or Ask Questions

BUSTLE: Bottom-up program-Synthesis Through Learning-guided Exploration


Jul 28, 2020
Augustus Odena, Kensen Shi, David Bieber, Rishabh Singh, Charles Sutton

Figure 1 for BUSTLE: Bottom-up program-Synthesis Through Learning-guided Exploration
Figure 2 for BUSTLE: Bottom-up program-Synthesis Through Learning-guided Exploration

  Access Paper or Ask Questions

Neural Program Synthesis with a Differentiable Fixer


Jun 19, 2020
Matej Balog, Rishabh Singh, Petros Maniatis, Charles Sutton

Figure 1 for Neural Program Synthesis with a Differentiable Fixer
Figure 2 for Neural Program Synthesis with a Differentiable Fixer
Figure 3 for Neural Program Synthesis with a Differentiable Fixer
Figure 4 for Neural Program Synthesis with a Differentiable Fixer

  Access Paper or Ask Questions

SCELMo: Source Code Embeddings from Language Models


Apr 28, 2020
Rafael - Michael Karampatsis, Charles Sutton

Figure 1 for SCELMo: Source Code Embeddings from Language Models
Figure 2 for SCELMo: Source Code Embeddings from Language Models
Figure 3 for SCELMo: Source Code Embeddings from Language Models
Figure 4 for SCELMo: Source Code Embeddings from Language Models
* 12 pages 
  Access Paper or Ask Questions

OptTyper: Probabilistic Type Inference by Optimising Logical and Natural Constraints


Apr 01, 2020
Irene Vlassi Pandi, Earl T. Barr, Andrew D. Gordon, Charles Sutton

Figure 1 for OptTyper: Probabilistic Type Inference by Optimising Logical and Natural Constraints
Figure 2 for OptTyper: Probabilistic Type Inference by Optimising Logical and Natural Constraints
Figure 3 for OptTyper: Probabilistic Type Inference by Optimising Logical and Natural Constraints
Figure 4 for OptTyper: Probabilistic Type Inference by Optimising Logical and Natural Constraints

  Access Paper or Ask Questions

Towards Modular Algorithm Induction


Feb 27, 2020
Daniel A. Abolafia, Rishabh Singh, Manzil Zaheer, Charles Sutton

Figure 1 for Towards Modular Algorithm Induction
Figure 2 for Towards Modular Algorithm Induction
Figure 3 for Towards Modular Algorithm Induction
Figure 4 for Towards Modular Algorithm Induction
* 10 pages, 4 figures, 2 tables 
  Access Paper or Ask Questions

Incremental Sampling Without Replacement for Sequence Models


Feb 21, 2020
Kensen Shi, David Bieber, Charles Sutton

Figure 1 for Incremental Sampling Without Replacement for Sequence Models
Figure 2 for Incremental Sampling Without Replacement for Sequence Models
Figure 3 for Incremental Sampling Without Replacement for Sequence Models
Figure 4 for Incremental Sampling Without Replacement for Sequence Models

  Access Paper or Ask Questions

Learning to Represent Programs with Property Signatures


Feb 13, 2020
Augustus Odena, Charles Sutton

Figure 1 for Learning to Represent Programs with Property Signatures
* ICLR 2020 
  Access Paper or Ask Questions

Learning to Fix Build Errors with Graph2Diff Neural Networks


Nov 04, 2019
Daniel Tarlow, Subhodeep Moitra, Andrew Rice, Zimin Chen, Pierre-Antoine Manzagol, Charles Sutton, Edward Aftandilian

Figure 1 for Learning to Fix Build Errors with Graph2Diff Neural Networks
Figure 2 for Learning to Fix Build Errors with Graph2Diff Neural Networks
Figure 3 for Learning to Fix Build Errors with Graph2Diff Neural Networks
Figure 4 for Learning to Fix Build Errors with Graph2Diff Neural Networks
* Submitted for review on Aug 23, 2019 
  Access Paper or Ask Questions

Robust Variational Autoencoders for Outlier Detection in Mixed-Type Data


Jul 15, 2019
Simão Eduardo, Alfredo Nazábal, Christopher K. I. Williams, Charles Sutton

Figure 1 for Robust Variational Autoencoders for Outlier Detection in Mixed-Type Data
Figure 2 for Robust Variational Autoencoders for Outlier Detection in Mixed-Type Data
Figure 3 for Robust Variational Autoencoders for Outlier Detection in Mixed-Type Data
Figure 4 for Robust Variational Autoencoders for Outlier Detection in Mixed-Type Data
* In submission to NeurIPS 2019 
  Access Paper or Ask Questions

Learning Semantic Annotations for Tabular Data


May 30, 2019
Jiaoyan Chen, Ernesto Jimenez-Ruiz, Ian Horrocks, Charles Sutton

Figure 1 for Learning Semantic Annotations for Tabular Data
Figure 2 for Learning Semantic Annotations for Tabular Data
Figure 3 for Learning Semantic Annotations for Tabular Data
Figure 4 for Learning Semantic Annotations for Tabular Data
* IJCAI 2019 
 * 7 pages 
  Access Paper or Ask Questions

Maybe Deep Neural Networks are the Best Choice for Modeling Source Code


Mar 13, 2019
Rafael-Michael Karampatsis, Charles Sutton

Figure 1 for Maybe Deep Neural Networks are the Best Choice for Modeling Source Code
Figure 2 for Maybe Deep Neural Networks are the Best Choice for Modeling Source Code
Figure 3 for Maybe Deep Neural Networks are the Best Choice for Modeling Source Code
Figure 4 for Maybe Deep Neural Networks are the Best Choice for Modeling Source Code

  Access Paper or Ask Questions

ColNet: Embedding the Semantics of Web Tables for Column Type Prediction


Nov 04, 2018
Jiaoyan Chen, Ernesto Jimenez-Ruiz, Ian Horrocks, Charles Sutton

Figure 1 for ColNet: Embedding the Semantics of Web Tables for Column Type Prediction
Figure 2 for ColNet: Embedding the Semantics of Web Tables for Column Type Prediction
Figure 3 for ColNet: Embedding the Semantics of Web Tables for Column Type Prediction
Figure 4 for ColNet: Embedding the Semantics of Web Tables for Column Type Prediction
* AAAI 2019 
  Access Paper or Ask Questions

Probabilistic Programming with Densities in SlicStan: Efficient, Flexible and Deterministic


Nov 02, 2018
Maria I. Gorinova, Andrew D. Gordon, Charles Sutton

Figure 1 for Probabilistic Programming with Densities in SlicStan: Efficient, Flexible and Deterministic
Figure 2 for Probabilistic Programming with Densities in SlicStan: Efficient, Flexible and Deterministic

  Access Paper or Ask Questions

HOUDINI: Lifelong Learning as Program Synthesis


Oct 28, 2018
Lazar Valkov, Dipak Chaudhari, Akash Srivastava, Charles Sutton, Swarat Chaudhuri

Figure 1 for HOUDINI: Lifelong Learning as Program Synthesis
Figure 2 for HOUDINI: Lifelong Learning as Program Synthesis
Figure 3 for HOUDINI: Lifelong Learning as Program Synthesis
Figure 4 for HOUDINI: Lifelong Learning as Program Synthesis

  Access Paper or Ask Questions

Deep Learning to Detect Redundant Method Comments


Jun 12, 2018
Annie Louis, Santanu Kumar Dash, Earl T. Barr, Charles Sutton

Figure 1 for Deep Learning to Detect Redundant Method Comments
Figure 2 for Deep Learning to Detect Redundant Method Comments
Figure 3 for Deep Learning to Detect Redundant Method Comments
Figure 4 for Deep Learning to Detect Redundant Method Comments
* 12 pages 
  Access Paper or Ask Questions

Ratio Matching MMD Nets: Low dimensional projections for effective deep generative models


May 31, 2018
Akash Srivastava, Kai Xu, Michael U. Gutmann, Charles Sutton

Figure 1 for Ratio Matching MMD Nets: Low dimensional projections for effective deep generative models
Figure 2 for Ratio Matching MMD Nets: Low dimensional projections for effective deep generative models
Figure 3 for Ratio Matching MMD Nets: Low dimensional projections for effective deep generative models
Figure 4 for Ratio Matching MMD Nets: Low dimensional projections for effective deep generative models
* Code: https://github.com/akashgit/RM-MMDnet 
  Access Paper or Ask Questions

A Survey of Machine Learning for Big Code and Naturalness


May 05, 2018
Miltiadis Allamanis, Earl T. Barr, Premkumar Devanbu, Charles Sutton

Figure 1 for A Survey of Machine Learning for Big Code and Naturalness
Figure 2 for A Survey of Machine Learning for Big Code and Naturalness
Figure 3 for A Survey of Machine Learning for Big Code and Naturalness
Figure 4 for A Survey of Machine Learning for Big Code and Naturalness
* Website accompanying this survey paper can be found at https://ml4code.github.io 
  Access Paper or Ask Questions

Variational Inference In Pachinko Allocation Machines


Apr 21, 2018
Akash Srivastava, Charles Sutton

Figure 1 for Variational Inference In Pachinko Allocation Machines
Figure 2 for Variational Inference In Pachinko Allocation Machines
Figure 3 for Variational Inference In Pachinko Allocation Machines
Figure 4 for Variational Inference In Pachinko Allocation Machines

  Access Paper or Ask Questions

Interpreting Deep Classifier by Visual Distillation of Dark Knowledge


Mar 11, 2018
Kai Xu, Dae Hoon Park, Chang Yi, Charles Sutton

Figure 1 for Interpreting Deep Classifier by Visual Distillation of Dark Knowledge
Figure 2 for Interpreting Deep Classifier by Visual Distillation of Dark Knowledge
Figure 3 for Interpreting Deep Classifier by Visual Distillation of Dark Knowledge
Figure 4 for Interpreting Deep Classifier by Visual Distillation of Dark Knowledge

  Access Paper or Ask Questions

VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning


Nov 06, 2017
Akash Srivastava, Lazar Valkov, Chris Russell, Michael U. Gutmann, Charles Sutton

Figure 1 for VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
Figure 2 for VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
Figure 3 for VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
Figure 4 for VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
* Published as a conference paper at NIPS, 2017 
  Access Paper or Ask Questions

Sequence-to-point learning with neural networks for nonintrusive load monitoring


Sep 18, 2017
Chaoyun Zhang, Mingjun Zhong, Zongzuo Wang, Nigel Goddard, Charles Sutton

Figure 1 for Sequence-to-point learning with neural networks for nonintrusive load monitoring
Figure 2 for Sequence-to-point learning with neural networks for nonintrusive load monitoring
Figure 3 for Sequence-to-point learning with neural networks for nonintrusive load monitoring
Figure 4 for Sequence-to-point learning with neural networks for nonintrusive load monitoring
* The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), 2018 
 * 8 pages, 3 figures 
  Access Paper or Ask Questions

Learning Continuous Semantic Representations of Symbolic Expressions


Jun 10, 2017
Miltiadis Allamanis, Pankajan Chanthirasegaran, Pushmeet Kohli, Charles Sutton

Figure 1 for Learning Continuous Semantic Representations of Symbolic Expressions
Figure 2 for Learning Continuous Semantic Representations of Symbolic Expressions
Figure 3 for Learning Continuous Semantic Representations of Symbolic Expressions
Figure 4 for Learning Continuous Semantic Representations of Symbolic Expressions
* Accepted to ICML 2017 
  Access Paper or Ask Questions

Autoencoding Variational Inference For Topic Models


Mar 04, 2017
Akash Srivastava, Charles Sutton

Figure 1 for Autoencoding Variational Inference For Topic Models
Figure 2 for Autoencoding Variational Inference For Topic Models
Figure 3 for Autoencoding Variational Inference For Topic Models
Figure 4 for Autoencoding Variational Inference For Topic Models

  Access Paper or Ask Questions

A Bayesian Network Model for Interesting Itemsets


Nov 11, 2016
Jaroslav Fowkes, Charles Sutton

Figure 1 for A Bayesian Network Model for Interesting Itemsets
Figure 2 for A Bayesian Network Model for Interesting Itemsets
Figure 3 for A Bayesian Network Model for Interesting Itemsets
Figure 4 for A Bayesian Network Model for Interesting Itemsets
* Supplementary material attached as Ancillary File; in PKDD 2016: European Conference on Machine Learning and Knowledge Discovery in Databases 
  Access Paper or Ask Questions