3 papers
cs.SE2026
JETO-Bench: A Reproducible Benchmark for Execution Time Improvement Patches in Java
Khashayar Etemadi, Zhendong Su
Automated fixing of performance issues is gaining attention, but existing benchmarks of execution time improvement patches (ETIPs) target Python, C++, or .NET and are fixed dataset…
cs.SE2026
CppPerf: An Automated Pipeline and Dataset for Performance-Improving C++ Commits
Tommy Ho, Khashayar Etemadi, Zhendong Su
Recent progress in automated repair of performance bugs demands realistic, executable benchmarks. However, existing C++ performance benchmarks are largely built from competitive pr…
cs.SE2024
API-guided Dataset Synthesis to Finetune Large Code Models
Zongjie Li, Daoyuan Wu, Shuai Wang +1
Large code models (LCMs), pre-trained on vast code corpora, have demonstrated remarkable performance across a wide array of code-related tasks. Supervised fine-tuning (SFT) plays a…