Yu Yu

Yu Yu

Auto-generated profile, based on publicly available information

Yu Yu

Shandong Normal University, School of Computer Science and Artificial Intelligence, Jinan, China

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 April 2026
Verified
Conference Paper
Open access
YYYu Yu
Yu Yu
CLChen Lyu
Chen Lyu
With the remarkable progress of Code Large Language Models (Code LLMs) in achieving semantic correctness, execution efficiency has become an increasingly important dimension for evaluating their practical utility. However, existing approaches typically treat full programs as a single optimization target during training, without explicitly modeling the structural factors that influence efficiency. As a result, although these models can generate semantically correct code, they fail to learn, at a fine-grained level, the underlying skeleton features that lead to efficient implementations. To address this limitation, we propose SkelDPO (Skeleton-Guided Direct Preference Optimization), a skeleton-guided preference optimization framework that systematically enhances the efficiency of code generation. SkelDPO first identifies efficient and inefficient implementations from the code dataset and, through comparative analysis, locates their efficiency-prone and inefficiency-prone points, forming alignment signals between efficiency and inefficiency skeletons. During training, a joint code and skeleton preference loss is introduced, enabling the model to learn semantic correctness while reinforcing its understanding of efficiency-critical components in code. We conduct comprehensive experiments on two efficiency-oriented benchmarks, Mercury and ENAMEL, using five representative backbone models. Results show that SkelDPO consistently surpasses existing methods: compared with SOTA method that relies solely on efficient and inefficient code preference optimization, it improves Pass@1, Beyond@1, and Effi@1 by 3–6%, 3–7%, and 2–5%, with greater improvements observed on complex tasks. Further analysis demonstrates that SkelDPO exhibits strong robustness to hyperparameter settings, and higher proportions of skeleton-based samples lead to greater improvements. Overall, SkelDPO provides a new perspective on skeleton-level efficiency alignment, breaking the limitation of conventional preference optimization that relies solely on correctness or efficiency pairs, and paving the way for interpretable and transferable efficient code generation. All datasets and source code are publicly available at: https://github.com/YYYY-YuYu/SkelDPO.

30 June 2026 in Proceedings of the ACM on Software Engineering
Verified
Journal Article
Open access
YYYu Yu
Yu Yu
ZSZhihong Sun
Zhihong Sun
JLJia Li
Jia Li
YWYao Wan
Yao Wan
CLChuanyi Li
Chuanyi Li
CLChen Lyu
Chen Lyu
Large Language Models (LLMs) are capable of generating syntactically correct and functionally complete programs, greatly streamlining software development. However, recent studies reveal that these programs typically execute substantially slower than human-optimized counterparts. Existing approaches to bridging this efficiency gap typically involve either iteratively optimizing code after generation or fine-tuning models on corpora of efficient code. Yet, these methods expose the model to efficiency signals only by mimicking complete, optimized solutions, without explicitly encoding the structural code patterns essential for achieving high runtime performance. Addressing this gap presents two core challenges: (1) extracting and representing latent, efficiency-oriented structural patterns embedded within complex syntax and control flows, and (2) effectively learning these patterns without destabilizing the semantic training of LLMs. To tackle these challenges, we propose EffiSkel, an effi ciency skel eton-guided framework that explicitly extracts and learns efficiency skeletons—abstract, reusable structural patterns underpinning efficient code—by leveraging three complementary strategies: lexical analysis based on token-frequency saliency, syntactic analysis using similarity over Abstract Syntax Trees (ASTs), and dynamic line-level profiling of execution time. These skeletons are integrated into a multi-task learning regime that jointly optimizes code generation and skeleton prediction, introducing an explicit inductive bias toward efficiency-aware code generation. Experiments across multiple programming languages and benchmarks demonstrate that EffiSkel significantly enhances both functional correctness and efficiency, resulting on Mercury with DeepSeek-Coder (6.7B) a +11.11% (vs. EffiCoder) and +3.71% (vs. CodeDPO) higher Efficiency Ratio (ER), and a +0.36 (vs. EffiCoder) and +0.22 (vs. CodeDPO) increase in Average Speedup (AS). These results highlight the effectiveness of explicitly modeling efficiency skeletons in improving the runtime performance of code generated by LLMs.