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 401423 of 423 papers

TitleStatusHype
Robot Action Selection Learning via Layered Dimension Informed Program SynthesisCode0
Novel positional encodings to enable tree-based transformersCode0
Enhancing Code Generation via Bidirectional Comment-Level Mutual GroundingCode0
ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)Code0
Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology ProblemsCode0
Knowledge Refactoring for Inductive Program SynthesisCode0
Knowledge-Driven Robot Program Synthesis from Human VR DemonstrationsCode0
Synthesize, Execute and Debug: Learning to Repair for Neural Program SynthesisCode0
Synthesizing Action Sequences for Modifying Model DecisionsCode0
Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesisCode0
Dynamic Neural Program Embedding for Program RepairCode0
Differentiable Functional Program InterpretersCode0
Knowledge-Driven Program Synthesis via Adaptive Replacement Mutation and Auto-constructed Subprogram ArchivesCode0
HumanEval on Latest GPT Models -- 2024Code0
HOUDINI: Lifelong Learning as Program SynthesisCode0
PanGu-Coder: Program Synthesis with Function-Level Language ModelingCode0
DeepSynth: Automata Synthesis for Automatic Task Segmentation in Deep Reinforcement LearningCode0
GRAN is superior to GraphRNN: node orderings, kernel- and graph embeddings-based metrics for graph generatorsCode0
Selecting Representative Examples for Program SynthesisCode0
GitHub Copilot AI pair programmer: Asset or Liability?Code0
What If: Generating Code to Answer Simulation QuestionsCode0
PLANS: Robust Program Learning from Neurally Inferred SpecificationsCode0
A probabilistic and multi-objective analysis of lexicase selection and epsilon-lexicase selectionCode0
Show:102550
← PrevPage 9 of 9Next →

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