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 5160 of 423 papers

TitleStatusHype
Search-Based Regular Expression Inference on a GPUCode1
Emergent Representations of Program Semantics in Language Models Trained on ProgramsCode1
Outline, Then Details: Syntactically Guided Coarse-To-Fine Code GenerationCode1
Improving Code Generation by Training with Natural Language FeedbackCode1
WikiCoder: Learning to Write Knowledge-Powered CodeCode1
xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and RetrievalCode1
Large Language Models for Code: Security Hardening and Adversarial TestingCode1
NeuRI: Diversifying DNN Generation via Inductive Rule InferenceCode1
PADL: Language-Directed Physics-Based Character ControlCode1
Execution-based Code Generation using Deep Reinforcement LearningCode1
Show:102550
← PrevPage 6 of 43Next →

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