Expert problem-solving is driven by powerful languages for thinking about problems and
their solutions. Acquiring expertise means learning these languages—systems of concepts …

This paper introduces corpus-guided top-down synthesis as a mechanism for synthesizing
library functions that capture common functionality from a corpus of programs in a domain …

Programs offer compactness and structure that makes them an attractive representation for
visual data. We explore how code rewriting can be used to improve systems for inferring …

We introduce ShapeCoder, the first system capable of taking a dataset of shapes,
represented with unstructured primitives, and jointly discovering (i) useful abstraction …

While large language models (LLMs) now excel at code generation, a key aspect of software
development is the art of refactoring: consolidating code into libraries of reusable and …

Anti-unification (AU) is a fundamental operation for generalization computation used for
inductive inference. It is the dual operation to unification, an operation at the foundation of …

Effective planning in the real world requires not only world knowledge, but the ability to
leverage that knowledge to build the right representation of the task at hand. Decades of …

Rewrite rules are critical in equality saturation, an increasingly popular technique in
optimizing compilers, synthesizers, and verifiers. Unfortunately, developing high-quality …

Understanding the interactions of agents trained with deep reinforcement learning is crucial
for deploying agents in games or the real world. In the former, unreasonable actions confuse …

Parametric CAD models encode entire families of shapes that should, in principle, be easy
for designers to explore. However, in practice, parametric CAD models can be difficult to …