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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Show Your Work: Scratchpads for Intermediate Computation with Language Models


Nov 30, 2021
Maxwell Nye, Anders Johan Andreassen, Guy Gur-Ari, Henryk Michalewski, Jacob Austin, David Bieber, David Dohan, Aitor Lewkowycz, Maarten Bosma, David Luan, Charles Sutton, Augustus Odena


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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

* Jacob and Augustus contributed equally 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning


Jul 06, 2021
Maxwell Nye, Michael Henry Tessler, Joshua B. Tenenbaum, Brenden M. Lake


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Communicating Natural Programs to Humans and Machines


Jun 15, 2021
Samuel Acquaviva, Yewen Pu, Marta Kryven, Catherine Wong, Gabrielle E Ecanow, Maxwell Nye, Theodoros Sechopoulos, Michael Henry Tessler, Joshua B. Tenenbaum

* equal contributions: (author 3, 4), (author 5,6,7) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Implicit Representations of Meaning in Neural Language Models


Jun 01, 2021
Belinda Z. Li, Maxwell Nye, Jacob Andreas

* 15 pages, 6 figures; accepted to ACL 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Representing Partial Programs with Blended Abstract Semantics


Dec 23, 2020
Maxwell Nye, Yewen Pu, Matthew Bowers, Jacob Andreas, Joshua B. Tenenbaum, Armando Solar-Lezama


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning


Jun 15, 2020
Kevin Ellis, Catherine Wong, Maxwell Nye, Mathias Sable-Meyer, Luc Cary, Lucas Morales, Luke Hewitt, Armando Solar-Lezama, Joshua B. Tenenbaum


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Write, Execute, Assess: Program Synthesis with a REPL


Jun 09, 2019
Kevin Ellis, Maxwell Nye, Yewen Pu, Felix Sosa, Josh Tenenbaum, Armando Solar-Lezama

* The first four authors contributed equally to this work 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Learning to Infer Program Sketches


Feb 17, 2019
Maxwell Nye, Luke Hewitt, Joshua Tenenbaum, Armando Solar-Lezama


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Are Efficient Deep Representations Learnable?


Jul 17, 2018
Maxwell Nye, Andrew Saxe

* Presented at ICLR 2018 Workshop 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email