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

Showing 301325 of 423 papers

TitleStatusHype
Neurosymbolic Deep Generative Models for Sequence Data with Relational Constraints0
FCR: Flow Chart Recognition Network for Program Synthesis0
Representing Partial Programs with Blended Abstract Semantics0
Tag-based regulation of modules in genetic programming improves context-dependent problem solvingCode0
Latent Programmer: Discrete Latent Codes for Program Synthesis0
PLANS: Neuro-Symbolic Program Learning from Videos0
Multi-Plane Program Induction with 3D Box Priors0
GRCNN: Graph Recognition Convolutional Neural Network for Synthesizing Programs from Flow Charts0
Learning to Execute Programs with Instruction Pointer Attention Graph Neural NetworksCode0
Dreaming with ARC0
Automated Generation of Executable Cross-Language Background Knowledge0
Goal-directed Generation of Discrete Structures with Conditional Generative Models0
Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design SequencesCode1
Optimal Neural Program Synthesis from Multimodal Specifications0
Adversarial Synthetic Datasets for Neural Program Synthesis0
SQUARES: A SQL Synthesizer Using Query Reverse EngineeringCode1
Type-driven Neural Programming by Example0
Process Discovery for Structured Program Synthesis0
Robot Action Selection Learning via Layered Dimension Informed Program SynthesisCode0
Code Building Genetic ProgrammingCode1
BUSTLE: Bottom-Up Program Synthesis Through Learning-Guided Exploration0
Semi-supervised Learning From Demonstration Through Program Synthesis: An Inspection Robot Case Study0
Synthesize, Execute and Debug: Learning to Repair for Neural Program SynthesisCode0
SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided DesignCode1
Programming by Rewards0
Show:102550
← PrevPage 13 of 17Next →

Benchmark Results

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