Zengyang Li

TLSS_ICFS: A novel two-stage cross-project defect prediction approach

Fu Hang, Ran Mo, Xinya Mu, Wei Ding et autres

cn (code pays fourni par la source)

PaletteID: Prototype-Composed Semantic Identifiers for Multimodal CTR Prediction

Huanyu Liu, Bin Chen, Hui Liu, Zengyang Li et autres

Multimodal information can improve the accuracy of click-through rate (CTR) prediction and effectively alleviate item cold-start and long-tail problems. Recent studies commonly discretize pretrained multimodal embeddings into semantic identifiers (SIDs), allowing the model to learn task-specific semantic representations for recommendation. However, existing …

Generalized Synchronization of Two-Layered Complex Dynamical Networks and Its Application to Robust Chaotic Encryption

Hui Liu, Weiren Zhou, Zengyang Li, Haibo Wan et autres

This paper proposes a robust chaotic secure encryption method based on the generalized synchronization of two-layered complex networks. Using a nonlinear mapping to realize generalized synchronization, the proposed scheme relaxes both the requirement for identical node dynamics and system parameters, which substantially …

cn (code pays fourni par la source)

CodeTeam: An LLM-Powered Multi-Agent Framework for Repository-Level Code Generation

Yifei Wang, R K Li, Peng Liang, Qiong Feng et autres

Natural language to repository generation (NL2Repo) requires a system to construct an entire software repository from a natural-language requirements document. Compared with function-level code generation, this task demands longer planning horizons, stable interfaces across files, and iterative debugging of cross-file inconsistencies. To …

Rule Taxonomy and Evolution in AI IDEs: A Mining and Survey Study

Guangzong Cai, Ruiyin Li, Peng Liang, Zengyang Li et autres

The adoption of AI-powered Integrated Development Environments (AI IDEs) has introduced "Rules" as a novel software artifact, allowing developers to persistently inject project-specific constraints and architectural guidelines into the context of Large Language Models (LLMs). Despite their role in aligning AI behavior …

Fine-Tuning Code Language Models to Detect Cross-Language Bugs

Zengyang Li, Yimeng Li, Binbin Huang, Peng Liang et autres

With the rapid development of software engineering technologies, multilingual programming, i.e., developing a program using multiple programming languages (PLs) collaboratively, has become increasingly popular. This practice is often adopted to reuse existing code, to leverage advantages of specific PLs, to satisfy various …

cn (code pays fourni par la source)

Beyond Functional Correctness: Design Issues in AI IDE-Generated Large-Scale Projects

Syed Mohammad Kashif, Ruiyin Li, Peng Liang, Amjed Tahir et autres

New generation of AI coding tools, including AI-powered IDEs equipped with agentic capabilities, can generate code within the context of the project. These AI IDEs are increasingly perceived as capable of producing project-level code at scale. However, there is limited empirical evidence …

Unveiling code clones in the Eclipse IIoT software ecosystem

Zengyang Li, Binbin Huang, Yimeng Li, Ran Mo et autres

cn (code pays fourni par la source)

Unveiling Code Clones in the Eclipse IIoT Software Ecosystem

Zengyang Li, Binbin Huang, Yimeng Li, Ran Mo et autres

Industrial Internet of Things (IIoT) has become a prominent topic recently, with an increasing number of IIoT OSS projects emerging, also within the Eclipse Foundation. Code cloning is a common practice that can adversely affect software maintenance. In the IIoT OSS domain, …

Unveiling Code Clones in the Eclipse IIoT Software Ecosystem

Zengyang Li, Binbin Huang, Yimeng Li, Ran Mo et autres

Industrial Internet of Things (IIoT) has become a prominent topic recently, with an increasing number of IIoT OSS projects emerging, also within the Eclipse Foundation. Code cloning is a common practice that can adversely affect software maintenance. In the IIoT OSS domain, …

cn (code pays fourni par la source)

A Multi-Dimensional Quality Evaluation of Code Generated by LLM-Based Tools across Multiple Programming Languages

Ruimeng Li, Ran Mo, Yao Zeng, Zili Liu et autres

Large Language Model (LLM)-based code generation tools have gained widespread adoption in software development. The code quality is an important concern that affects the practical usefulness of generated code suggestions. However, comprehensive evaluations of these tools’ code quality remain limited. In this …

cn (code pays fourni par la source)

Unveiling the Role of ChatGPT in Software Development: Insights from Developer–ChatGPT Interactions on GitHub

Ruiyin Li, Peng Liang, Yifei Wang, Yangxiao Cai et autres

The advent of Large Language Models (LLMs) has introduced a new paradigm in Software Engineering (SE), with generative AI tools like ChatGPT gaining widespread adoption among developers. While ChatGPT’s potential has been extensively discussed, empirical evidence about how developers actually use LLMs’ …

cn, sg (code pays fourni par la source)