32 citations · 49 across the 6 of their papers we have counts for
6 papers
Condor: A Code Discriminator Integrating General Semantics with Code Details
Qingyuan Liang, Zhao Zhang, Chen Liu +9
LLMs demonstrate significant potential across various software engineering tasks. However, they still face challenges in generating correct code on the first attempt when addressin…
OrdinalFix: Fixing Compilation Errors via Shortest-Path CFL Reachability
Wenjie Zhang, Guancheng Wang, Junjie Chen +3
The development of correct and efficient software can be hindered by compilation errors, which must be fixed to ensure the code's syntactic correctness and program language constra…
Lyra: A Benchmark for Turducken-Style Code Generation
Qingyuan Liang, Zeyu Sun, Qihao Zhu +4
Recently, neural techniques have been used to generate source code automatically. While promising for declarative languages, these approaches achieve much poorer performance on dat…
A Syntax-Guided Edit Decoder for Neural Program Repair
Qihao Zhu, Zeyu Sun, Yuan-an Xiao +4
Automated Program Repair (APR) helps improve the efficiency of software development and maintenance. Recent APR techniques use deep learning, particularly the encoder-decoder archi…
Generalized Equivariance and Preferential Labeling for GNN Node Classification
Zeyu Sun, Wenjie Zhang, Lili Mou +3
Existing graph neural networks (GNNs) largely rely on node embeddings, which represent a node as a vector by its identity, type, or content. However, graphs with unattributed nodes…
NLocalSAT: Boosting Local Search with Solution Prediction
Wenjie Zhang, Zeyu Sun, Qihao Zhu +4
The Boolean satisfiability problem (SAT) is a famous NP-complete problem in computer science. An effective way for solving a satisfiable SAT problem is the stochastic local search…