Publications

* denotes equal contribution. + denotes equal advising.

ICLR
2022
CrossBeam: Learning to Search in Bottom-Up Program SynthesisKensen Shi*, Hanjun Dai*, Kevin Ellis,+ Charles Sutton+
ICLR
2022
Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous InterfaceTuan Anh Le, Katherine M. Collins, Luke Hewitt, Kevin Ellis, Siddharth N, Samuel J. Gershman, Joshua B. Tenenbaum
AAAI
2022
Scaling Neural Program Synthesis with Distribution-based SearchNathanaël Fijalkow, Guillaume Lagarde, Théo Matricon, Kevin Ellis, Pierre Ohlmann, Akarsh Potta
PLDI
2021
DreamCoder: Bootstrapping Inductive Program Synthesis with Wake-Sleep Library LearningKevin Ellis, Catherine Wong, Maxwell Nye, Mathias Sablé-Meyer, Lucas Morales, Luke Hewitt, Luc Cary, Armando Solar-Lezama, Joshua B. Tenenbaum
FnT in
Programming
Languages
2021
Neurosymbolic ProgrammingSwarat Chaudhuri, Kevin Ellis, Oleksandr Polozov, Rishabh Singh, Armando Solar-Lezama, Yisong Yue
Artificial
Intelligence
2021
Making sense of raw inputRichard Evans, Matko Bošnjak, Lars Buesing, Kevin Ellis, David Pfau, Pushmeet Kohli, Marek Sergot
ICML
2021
Leveraging natural language for program search and abstraction learningCatherine Wong, Kevin Ellis, Josh Tenenbaum, Jacob Andreas
CogSci
2021
Phonological Interactions, Process Types, and Minimum Description Length PrinciplesChristopher Yang, Kevin Ellis
NeurIPS
2020, Oral
Learning abstract structure for drawing by efficient motor program inductionLucas Y. Tian, Kevin Ellis, Marta Kryven, Joshua B. Tenenbaum
NeurIPS
2020
Program Synthesis with Pragmatic CommunicationYewen Pu, Kevin Ellis, Marta Kryven, Joshua B. Tenenbaum, Armando Solar-Lezama
NeurIPS
2019
Write, Execute, Assess: Program Synthesis with a REPLKevin Ellis*, Maxwell Nye*, Yewen Pu*, Felix Sosa*, Joshua B. Tenenbaum, Armando Solar-Lezama
ICLR
2019
Learning to Infer and Execute 3D Shape ProgramsYonglong Tian, Andrew Luo, Xingyuan Sun, Kevin Ellis, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu
Topics in
Cognitive Science
2019
Five ways in which computational modeling can help advance cognitive science: lessons from Artificial Grammar LearningWillem Zuidema, Robert M. French, Raquel G. Alhama, Kevin Ellis, Tim O’Donnell, Tim Sainburgh, Tim Gentner
NeurIPS
2018, Spotlight
Learning Libraries of Subroutines for Neurally-Guided Bayesian Program InductionKevin Ellis, Lucas Morales, Mathias Sablé-Meyer, Armando Solar-Lezama, Joshua B. Tenenbaum
NeurIPS
2018, Spotlight
Learning to Infer Graphics Programs from Hand-Drawn ImagesKevin Ellis, Daniel Ritchie, Armando Solar-Lezama, Joshua B. Tenenbaum
IJCAI
2017
Learning to Learn Programs from Examples: Going Beyond Program StructureKevin Ellis, Sumit Gulwani
NeurIPS
2016
Sampling for Bayesian Program LearningKevin Ellis, Armando Solar-Lezama, Joshua B. Tenenbaum
NeurIPS
2015
Unsupervised Learning by Program SynthesisKevin Ellis, Armando Solar-Lezama, Joshua B. Tenenbaum
AAAI
Symposium
2015
Dimensionality Reduction via Program InductionKevin Ellis, Eyal Dechter, Joshua B. Tenenbaum. At the AAAI Symposium on Knowledge Representation and Reasoning: Integrating Symbolic and Neural Approaches
ECAI
2014
Bias reformulation for one-shot function inductionDianhuan Lin, Eyal Dechter, Kevin Ellis, Joshua B. Tenenbaum, Stephen Muggleton