7 papers
ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning
Lingxiao Tang, He Ye, Zhaoyang Chu +4
Code LLMs still struggle with code execution reasoning, especially in smaller models. Existing methods rely on supervised fine-tuning (SFT) with teacher-generated explanations, pri…
Bridging Code Graphs and Large Language Models for Better Code Understanding
Zeqi Chen, Zhaoyang Chu, Yi Gui +3
Large Language Models (LLMs) have demonstrated remarkable performance in code intelligence tasks such as code generation, summarization, and translation. However, their reliance on…
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…
Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency
Chenlong Wang, Yuanning Feng, Dongping Chen +3
Recent advances in large reasoning models have enabled complex, step-by-step reasoning but often introduce significant overthinking, resulting in verbose and redundant outputs that…
CODESYNC: Synchronizing Large Language Models with Dynamic Code Evolution at Scale
Chenlong Wang, Zhaoyang Chu, Zhengxiang Cheng +6
Large Language Models (LLMs) have exhibited exceptional performance in software engineering yet face challenges in adapting to continually evolving code knowledge, particularly reg…
How to Select Pre-Trained Code Models for Reuse? A Learning Perspective
Zhangqian Bi, Yao Wan, Zhaoyang Chu +5
Pre-training a language model and then fine-tuning it has shown to be an efficient and effective technique for a wide range of code intelligence tasks, such as code generation, cod…