Abstract: Large Language Models (LLMs) have demonstrated unprecedented capability in code generation. However, LLM-generated code is still plagued with a wide range of functional errors, especially ...

With the aggregation results, we would like to compare the performance of aggregation models associated with different loss functions. However, aggregation models can not be compared based on the ...

Abstract: In the twilight of Moore’s law, optimizing program performance has emerged as a central focus in computer architecture research. Yet, high-level source optimization remains challenging due ...