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

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Copy that! Editing Sequences by Copying Spans

Jun 08, 2020
Sheena Panthaplackel, Miltiadis Allamanis, Marc Brockschmidt


  Access Paper or Ask Questions

Analyzing Privacy Loss in Updates of Natural Language Models

Jan 14, 2020
Shruti Tople, Marc Brockschmidt, Boris Köpf, Olga Ohrimenko, Santiago Zanella-Béguelin


  Access Paper or Ask Questions

Disentangling Interpretable Generative Parameters of Random and Real-World Graphs

Nov 06, 2019
Niklas Stoehr, Emine Yilmaz, Marc Brockschmidt, Jan Stuehmer

* 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Workshop on Graph Representation Learning 

  Access Paper or Ask Questions

CodeSearchNet Challenge: Evaluating the State of Semantic Code Search

Sep 27, 2019
Hamel Husain, Ho-Hsiang Wu, Tiferet Gazit, Miltiadis Allamanis, Marc Brockschmidt


  Access Paper or Ask Questions

Program Synthesis and Semantic Parsing with Learned Code Idioms

Jul 23, 2019
Richard Shin, Miltiadis Allamanis, Marc Brockschmidt, Oleksandr Polozov


  Access Paper or Ask Questions

GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation

Jun 28, 2019
Marc Brockschmidt


  Access Paper or Ask Questions

Structured Neural Summarization

Nov 05, 2018
Patrick Fernandes, Miltiadis Allamanis, Marc Brockschmidt


  Access Paper or Ask Questions

Learning to Represent Edits

Oct 31, 2018
Pengcheng Yin, Graham Neubig, Miltiadis Allamanis, Marc Brockschmidt, Alexander L. Gaunt


  Access Paper or Ask Questions

Robust Text-to-SQL Generation with Execution-Guided Decoding

Sep 13, 2018
Chenglong Wang, Kedar Tatwawadi, Marc Brockschmidt, Po-Sen Huang, Yi Mao, Oleksandr Polozov, Rishabh Singh


  Access Paper or Ask Questions

Constrained Graph Variational Autoencoders for Molecule Design

May 23, 2018
Qi Liu, Miltiadis Allamanis, Marc Brockschmidt, Alexander L. Gaunt

* 8 pages, 5 figures 

  Access Paper or Ask Questions

Generative Code Modeling with Graphs

May 22, 2018
Marc Brockschmidt, Miltiadis Allamanis, Alexander L. Gaunt, Oleksandr Polozov


  Access Paper or Ask Questions

Learning to Represent Programs with Graphs

May 04, 2018
Miltiadis Allamanis, Marc Brockschmidt, Mahmoud Khademi

* Published in ICLR 2018. arXiv admin note: text overlap with arXiv:1705.07867 

  Access Paper or Ask Questions

Graph Partition Neural Networks for Semi-Supervised Classification

Mar 16, 2018
Renjie Liao, Marc Brockschmidt, Daniel Tarlow, Alexander L. Gaunt, Raquel Urtasun, Richard Zemel


  Access Paper or Ask Questions

Gated Graph Sequence Neural Networks

Sep 22, 2017
Yujia Li, Daniel Tarlow, Marc Brockschmidt, Richard Zemel

* Published as a conference paper in ICLR 2016. Fixed a typo 

  Access Paper or Ask Questions

SmartPaste: Learning to Adapt Source Code

May 22, 2017
Miltiadis Allamanis, Marc Brockschmidt


  Access Paper or Ask Questions

DeepCoder: Learning to Write Programs

Mar 08, 2017
Matej Balog, Alexander L. Gaunt, Marc Brockschmidt, Sebastian Nowozin, Daniel Tarlow

* Submitted to ICLR 2017 

  Access Paper or Ask Questions

Differentiable Programs with Neural Libraries

Mar 02, 2017
Alexander L. Gaunt, Marc Brockschmidt, Nate Kushman, Daniel Tarlow


  Access Paper or Ask Questions

Differentiable Functional Program Interpreters

Mar 02, 2017
John K. Feser, Marc Brockschmidt, Alexander L. Gaunt, Daniel Tarlow


  Access Paper or Ask Questions

Summary - TerpreT: A Probabilistic Programming Language for Program Induction

Dec 02, 2016
Alexander L. Gaunt, Marc Brockschmidt, Rishabh Singh, Nate Kushman, Pushmeet Kohli, Jonathan Taylor, Daniel Tarlow

* 7 pages, 2 figures, 4 tables in 1st Workshop on Neural Abstract Machines & Program Induction (NAMPI), @NIPS 2016 

  Access Paper or Ask Questions

TerpreT: A Probabilistic Programming Language for Program Induction

Aug 15, 2016
Alexander L. Gaunt, Marc Brockschmidt, Rishabh Singh, Nate Kushman, Pushmeet Kohli, Jonathan Taylor, Daniel Tarlow

* 50 pages, 20 figures, 4 tables 

  Access Paper or Ask Questions