SOTAVerified

Program Synthesis

Program synthesis is the process of automatically generating a program or code snippet that satisfies a given specification or set of requirements. This can include generating code from a formal specification, a natural language description, or example inputs and outputs. The primary goal of program synthesis is to minimize human intervention in the coding process, reduce errors, and improve productivity.

Program synthesis often involves the use of advanced algorithms, artificial intelligence, and machine learning techniques to search the space of possible programs that meet the given constraints. This process can be guided by a variety of techniques, such as constraint solving, symbolic execution, and genetic algorithms.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 326–350 of 423 papers

TitleStatusHype
Program Synthesis with Pragmatic Communication—0
Learning Web-based Procedures by Reasoning over Explanations and Demonstrations in Context—0
Information-theoretic User Interaction: Significant Inputs for Program Synthesis—0
Neural Program Synthesis with a Differentiable Fixer—0
IReEn: Reverse-Engineering of Black-Box Functions via Iterative Neural Program Synthesis—0
DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learningCode1
PLANS: Robust Program Learning from Neurally Inferred SpecificationsCode0
Graph-based, Self-Supervised Program Repair from Diagnostic FeedbackCode1
Guiding Program Synthesis by Learning to Generate ExamplesCode1
Learning large logic programs by going beyond entailment—0
Knowledge Refactoring for Inductive Program SynthesisCode0
Creating Synthetic Datasets via Evolution for Neural Program Synthesis—0
TF-Coder: Program Synthesis for Tensor ManipulationsCode1
Learning Compositional Rules via Neural Program SynthesisCode1
Incremental Sampling Without Replacement for Sequence ModelsCode1
Improving Molecular Design by Stochastic Iterative Target AugmentationCode1
Evaluating Sequence-to-Sequence Learning Models for If-Then Program SynthesisCode0
Unsupervised Program Synthesis for Images By Sampling Without Replacement—0
CounterExample Guided Neural Synthesis—0
Comparison of Syntactic and Semantic Representations of Programs in Neural EmbeddingsCode3
Generating Programmatic Referring Expressions via Program SynthesisCode0
Towards Neural-Guided Program Synthesis for Linear Temporal Logic Specifications—0
Adaptive Correlated Monte Carlo for Contextual Categorical Sequence GenerationCode0
Synthetic Datasets for Neural Program Synthesis—0
Novel positional encodings to enable tree-based transformersCode0
Show:102550
← PrevPage 14 of 17Next →
All datasetsSPoC TestPSPoC TestWAlgoLisp

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DrRepairSuccess rate @budget 10038.5—Unverified
2Multiclass localizerSuccess rate @budget 10034.2—Unverified
#ModelMetricClaimedVerifiedStatus
1DrRepairSuccess rate @budget 10057—Unverified
2Multiclass localizerSuccess rate @budget 10053.7—Unverified
#ModelMetricClaimedVerifiedStatus
1CodeTrans-MT-TF-SmallAccuracy90.31—Unverified