4 papers
SemLoc: Structured Grounding of Free-Form LLM Reasoning for Fault Localization
Zhaorui Yang, Haichao Zhu, Qian Zhang +2
Large language models (LLMs) can describe what a piece of code should compute, but they do so in free-form text. Such text cannot be checked against program executions, and it does…
Needle in the Repo: A Benchmark for Maintainability in AI-Generated Repository Edits
Haichao Zhu, Qian Zhang, Jiyuan Wang +2
AI coding agents can now complete complex programming tasks, but existing evaluations largely emphasize behavioral correctness and often overlook maintainability risks such as weak…
Learning Proposes, Geometry Disposes: A Modular Framework for Efficient Spatial Reasoning
Haichao Zhu, Zhaorui Yang, Qian Zhang
Spatial perception aims to estimate camera motion and scene structure from visual observations, a problem traditionally addressed through geometric modeling and physical consistenc…
Generating Highly Structured Test Inputs Leveraging Constraint-Guided Graph Refinement
Zhaorui Yang, Yuxin Qiu, Haichao Zhu +1
[Context] Modern AI applications increasingly process highly structured data, such as 3D meshes and point clouds, where test input generation must preserve both structural and sema…