activity
20242026
most citedSifting through the Chaff: On Utilizing Execution Feedback for Ranking the Generated Code Candidates

1 citations · 1 across the 5 of their papers we have counts for

collaborators
Showing cs.SEShow all

6 papers · 1 filter

cs.SE2026

Chiseling Out Efficiency: Structured Skeleton Supervision for Efficient Code Generation

Yu Yu, Zhihong Sun, Jia Li +8

Large Language Models (LLMs) are capable of generating syntactically correct and functionally complete programs, greatly streamlining software development. However, recent studies…

cs.SE2025

Ensembling Large Language Models for Code Vulnerability Detection: An Empirical Evaluation

Zhihong Sun, Jia Li, Yao Wan +7

Code vulnerability detection is crucial for ensuring the security and reliability of modern software systems. Recently, Large Language Models (LLMs) have shown promising capabiliti…

cs.SE2025

Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning

Zhaoyang Chu, Yao Wan, Zhikun Zhang +7

While Code Language Models (CLMs) have demonstrated superior performance in software engineering tasks such as code generation and summarization, recent empirical studies reveal a…

cs.SE20241 cited

Sifting through the Chaff: On Utilizing Execution Feedback for Ranking the Generated Code Candidates

Zhihong Sun, Yao Wan, Jia Li +4

Large Language Models (LLMs), such as GPT-4, StarCoder, and CodeLlama, are transforming the way developers approach programming by automatically generating code based on given natu…

cs.SE20245 cited

Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs

Zhihong Sun, Chen Lyu, Bolun Li +4

Large Language Models (LLMs) have recently made significant advances in code generation through the 'Chain-of-Thought' prompting technique. This technique empowers the model to aut…

cs.SE2024

IRCoCo: Immediate Rewards-Guided Deep Reinforcement Learning for Code Completion

Bolun Li, Zhihong Sun, Tao Huang +5

Code completion aims to enhance programming productivity by predicting potential code based on the current programming context. Recently, pretrained language models (LMs) have beco…