functional correctness

6 papers

• EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code
• Let a Neural Network be Your Invariant
• MaintainCoder: Maintainable Code Generation Under Dynamic Requirements
• QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code
• QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation
• Training Language Models to Generate Quality Code with Program Analysis Feedback