Pengyu Nie

Code2LoRA introduces a hypernetwork framework to efficiently inject repository-specific knowledge into code language models using LoRA adapters, supporting both static and evolving codebases.

The paper proposes Fuzzy-Function Programming and introduces Program-as-Weights (PAW), a compact, locally-executable neural artifact for everyday programming tasks.

This paper investigates the relationship between bug report features and repair success for automated program repair agents, finding that concrete, executable, and well-localized information is most beneficial.