11 papers
CogAdapt: Cognition-informed Sparse Adaptation of Code LLMs
Yueke Zhang, Zihan Fang, Kevin Leach +1
Large language models (LLMs) have become increasingly capable of generating code. However, achieving stronger code-generation performance still often relies on costly model adaptat…
STILL: Recovering Lowered STL Semantics for LLM-assisted C++ Decompilation
Xiaohan Wang, Kevin Leach
LLM-assisted decompilation improves readability and re-executability, but still underperforms on stripped C++ functions that use the Standard Template Library (STL). Compilation, o…
GraphAlignCoder: Aligning Program and Proof Graphs for Code Generation
Yueke Zhang, Zihan Fang, Kevin Leach +1
Code large language models (LLMs) can generate syntactically plausible programs that nevertheless violate hidden semantic constraints. Existing execution-feedback training methods…
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…
VERITAS: Verifier-Guided Proof Search for Zero-Shot Formal Theorem Proving
Manish Acharya, Zhenyu Liao, Yueke Zhang +3
LLM-based formal provers often collapse rich verifier signals (syntax errors, type mismatches, partial goal progress) into a binary pass/fail bit. We present VERITAS, a zero-shot f…
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…
SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair
Yifan Zhang, Jieyu Li, Kexin Pei +2
Large Language Models (LLMs) can generate plausible code patches, but plausibility is not enough for automated repair: a patch must compile, pass tests, and remove the target vulne…
EyeLayer: Integrating Human Attention Patterns into LLM-Based Code Summarization
Jiahao Zhang, Yifan Zhang, Kevin Leach +1
Code summarization is the task of generating natural language descriptions of source code, which is critical for software comprehension and maintenance. While large language models…
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…
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…
EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention
Yifan Zhang, Chen Huang, Yueke Zhang +5
Code Language Models (CodeLLMs) learn token importance from data correlations, whereas human developers attend selectively to semantically salient code. We present EyeMulator, a mo…