7 papers
SCOPE: Leveraging Subgoal Critiques for Code Generation
Yueke Zhang, Yifan Zhang, Zihan Fang +3
Code generation with large language models (LLMs) remains unreliable because generated programs can appear correct while still violating key semantic requirements in the natural la…
DPO-F+: Aligning Code Repair Feedback with Developers' Preferences
Zihan Fang, Yifan Zhang, Yueke Zhang +2
Large Language Models (LLMs) are increasingly used in software engineering tasks, especially code repair. However, developers often struggle to interpret model outputs, limiting ef…
Constraint-Guided Multi-Agent Decompilation for Executable Binary Recovery
Yifan Zhang, Xiaohan Wang, Yueke Zhang +2
Decompilation -- recovering source code from compiled binaries -- is essential for security analysis, malware reverse engineering, and legacy software maintenance. However, existin…
CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement
Yueke Zhang, Yifan Zhang, Kevin Leach +1
While Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, they often produce solutions that lack guarantees of correctness, robustness, and e…
MalMixer: Few-Shot Malware Classification with Retrieval-Augmented Semi-Supervised Learning
Jiliang Li, Yifan Zhang, Yu Huang +1
Recent growth and proliferation of malware have tested practitioners ability to promptly classify new samples according to malware families. In contrast to labor-intensive reverse…
Enhancing Code LLM Training with Programmer Attention
Yifan Zhang, Chen Huang, Zachary Karas +3
Human attention provides valuable yet underexploited signals for code LLM training, offering a perspective beyond purely machine-driven attention. Despite the complexity and cost o…