← Search

Weiyi Shang

2 accepted papers

2025

More Than Just Functional: LLM-as-a-Critique for Efficient Code Generation

NeurIPS 2025poster

Large language models (LLMs) have demonstrated remarkable progress in generating functional code, leading to numerous AI-based coding program tools. However, their reliance on the perplexity objective during both training and inference primarily emphasizes functionality, often at the expense of effi…

Cited by 0SourceScholar
2024

EffiBench: Benchmarking the Efficiency of Automatically Generated Code

NeurIPS 2024poster

Code generation models have increasingly become integral to aiding software development. Although current research has thoroughly examined the correctness of the code produced by code generation models, a vital aspect that plays a pivotal role in green computing and sustainability efforts — the effi…