• Publications
  • Influence
Combinatorial sketching for finite programs
TLDR
SKETCH is a language for finite programs with linguistic support for sketching and its combinatorial synthesizer is complete for the class of finite programs, guaranteed to complete any sketch in theory, and in practice has scaled to realistic programming problems.
Syntax-guided synthesis
TLDR
This work describes three different instantiations of the counter-example-guided-inductive-synthesis (CEGIS) strategy for solving the synthesis problem, reports on prototype implementations, and presents experimental results on an initial set of benchmarks.
Program synthesis by sketching
TLDR
Sketching is introduced, a new style of synthesis that offers a fresh approach to the synergy problem and shows that sketching is a viable approach to making synthesis practical in a general programming context.
Verifiable Reinforcement Learning via Policy Extraction
TLDR
VIPER, an algorithm that combines ideas from model compression and imitation learning to learn decision tree policies guided by a DNN policy and its Q-function, is proposed and it is shown that it substantially outperforms two baselines.
Program sketching
TLDR
CEGIS combines a SAT-based inductive synthesizer with an automated validation procedure, a bounded model-checker, that checks whether the candidate implementation produced by inductive synthesis is indeed correct and to produce new counterexamples.
QuixBugs: a multi-lingual program repair benchmark set based on the quixey challenge
TLDR
QuixBugs is presented, consisting of 40 programs translated to both Python and Java, each with a bug on a single line, based on problems from the Quixey Challenge, where programmers were given a short buggy program and 1 minute to fix the bug.
Automated feedback generation for introductory programming assignments
TLDR
A simple language for describing error models in terms of correction rules is introduced, and a rule-directed translation strategy is formally defined that reduces the problem of finding minimal corrections in an incorrect program to the problems of synthesizing a correct program from a sketch.
Program synthesis from polymorphic refinement types
TLDR
The tool was able to synthesize more complex programs than those reported in prior work, as well as most of the benchmarks tackled by existing synthesizers, often starting from a more concise and intuitive user input.
Learning to Infer Program Sketches
TLDR
This work proposes a method for dynamically integrating pattern recognition and explicit reasoning in a program synthesis system, and achieves state-of-the-art performance on a dataset of simple English description-to-code programming problems.
The Sketching Approach to Program Synthesis
TLDR
This paper describes the sketching approach to program synthesis, including the details of the Sketch language and synthesizer, and some of the techniques that make synthesis from sketches possible.
...
1
2
3
4
5
...