Sotabase

Career

· Assistant Professor, Cornell University2021–
· Research Scientist, Common Sense Machines2020–2021
· PhD in Cognitive Science, Massachusetts Institute of Technology2014–2020
· B.S. in Physics, Massachusetts Institute of Technology2010–2014
· Cornell

Publications (87)

Learning to Infer Graphics Programs from Hand-Drawn Images
Neural Information Processing Systems · 2017
242
cited
DreamCoder: growing generalizable, interpretable knowledge with wake–sleep Bayesian program learning
Philosophical Transactions of the Royal Society A · 2020
228
cited
DreamCoder: bootstrapping inductive program synthesis with wake-sleep library learning
ACM-SIGPLAN Symposium on Programming Language Design and Implementation · 2021
223
cited
Write, Execute, Assess: Program Synthesis with a REPL
Neural Information Processing Systems · 2019
179
cited
Learning to Infer and Execute 3D Shape Programs
International Conference on Learning Representations · 2019
152
cited
Bias reformulation for one-shot function induction
European Conference on Artificial Intelligence · 2014
101
cited
Neurosymbolic Programming
Found. Trends Program. Lang. · 2021
100
cited
Unsupervised Learning by Program Synthesis
Neural Information Processing Systems · 2015
79
cited
Learning Libraries of Subroutines for Neurally-Guided Bayesian Program Induction
Neural Information Processing Systems · 2018
77
cited
Top-Down Synthesis for Library Learning
Proc. ACM Program. Lang. · 2022
73
cited
Leveraging Language to Learn Program Abstractions and Search Heuristics
International Conference on Machine Learning · 2021
59
cited
A language of thought for the mental representation of geometric shapes
Cognitive Psychology · 2021
57
cited
Learning abstract structure for drawing by efficient motor program induction
Neural Information Processing Systems · 2020
41
cited
Library learning for neurally-guided Bayesian program induction
Neural Information Processing Systems · 2018
29
cited
CrossBeam: Learning to Search in Bottom-Up Program Synthesis
International Conference on Learning Representations · 2022
28
cited
Sampling for Bayesian Program Learning
Neural Information Processing Systems · 2016
28
cited
Program Synthesis with Pragmatic Communication
Neural Information Processing Systems · 2020
25
cited
Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language
Neural Information Processing Systems · 2023
23
cited
Synthesizing theories of human language with Bayesian program induction
Nature Communications · 2022
23
cited
Symbolic metaprogram search improves learning efficiency and explains rule learning in humans
Nature Communications · 2024
19
cited
Sotabase
Kevin Ellis | Researcher Profile | Sotabase | Sotabase