Explanipedia

Framework-Aware Code Generation with API Knowledge Graph-Constructed Data: A Study on HarmonyOS Open

Zheng Pei, Xin Peng · 2025

In the context of software frameworks with limited resources (such as HarmonyOS), large language models (LLMs) often exhibit poor code generation performance because they lack sufficient exposure to such environments during pre-training. A…

EvoDev: An Iterative Feature-Driven Framework for End-to-End Software Development with LLM-based Agents Open

Junwei Liu, Xu Chen, Tong Bai, Weitong Chen, Kok-Cheong Wong , et al. · 2025

Recent advances in large language model agents offer the promise of automating end-to-end software development from natural language requirements. However, existing approaches largely adopt linear, waterfall-style pipelines, which oversimp…

Rapid ranking of thermal safety realized by accelerating rate calorimetry correlating with small-scale slow cook-off: A case study of four melt-castable explosives Open

Peng Zhu, Zhi-yuan Jin, Xin Peng, Yu Qian, Sitong Chen , et al. · 2025

Code Digital Twin: Empowering LLMs with Tacit Knowledge for Complex Software Development Open

Xin Peng, Chong Wang · 2025

Recent advances in large language models (LLMs) have demonstrated strong capabilities in software engineering tasks, raising expectations of revolutionary productivity gains. However, enterprise software development is largely driven by in…

TigAug: Data Augmentation for Testing Traffic Light Detection in Autonomous Driving Systems Open

Y. P. Lu, Dong Wang, Kaifeng Huang, Bihuan Chen, Xin Peng · 2025

Autonomous vehicle technology has been developed in the last decades with recent advances in sensing and computing technology. There is an urgent need to ensure the reliability and robustness of autonomous driving systems (ADSs). Despite t…

Structure-Aware, Diagnosis-Guided ECU Firmware Fuzzing Open

Qing‐Quan Chen, Kun Hu, Shi-Hao Gong, Bihuan Chen, Zikui Kong , et al. · 2025

Electronic Control Units (ECUs), providing a wide range of functions from basic control functions to safety-critical functions, play a critical role in modern vehicles. Fuzzing has emerged as an effective approach to ensure the functional …

RouthSearch: Inferring PID Parameter Specification for Flight Control Program by Coordinate Search Open

Siao Wang, Zhen Dong, Hui Li, Liwei Shen, Xin Peng , et al. · 2025

Flight control programs are widely used in unmanned aerial vehicles (UAVs) to manage and maintain UAVs’ flying behaviors dynamically. These flight control programs include a PID control module that takes three user-configurable PID paramet…

Recurring Vulnerability Detection: How Far Are We? Open

Yuhua Cao, Susheng Wu, Ruisi Wang, Bihuan Chen, Yiheng Huang , et al. · 2025

With the rapid development of open-source software, code reuse has become a common practice to accelerate development. However, it leads to inheritance from the original vulnerability, which recurs at the reusing projects, known as recurri…

EnvGuard: Guaranteeing Environment-Centric Safety and Security Properties in Web of Things System Open

Bingkun Sun, Jialin Ren, J. Luo, Liwei Shen, Yu‐Ju Lu , et al. · 2025

Mystique: Automated Vulnerability Patch Porting with Semantic and Syntactic-Enhanced LLM Open

Susheng Wu, Ruisi Wang, Yuhua Cao, Bihuan Chen, Zhuotong Zhou , et al. · 2025

Branching repositories facilitates efficient software development but can also inadvertently propagate vulnerabilities. When an original branch is patched, other unfixed branches remain vulnerable unless the patch is successfully ported. H…

Detecting and Handling WoT Violations by Learning Physical Interactions from Device Logs Open

Bingkun Sun, Shihua Sun, Jialin Ren, Mingming Hu, Kun Hu , et al. · 2025

The Web of Things (WoT) system standardizes the integration of ubiquitous IoT devices in physical environments, enabling various software applications to automatically sense and regulate the physical environment. While providing convenienc…

Towards Better Code Generation: Adaptive Decoding with Uncertainty Guidance Open

Kaifeng He, Mingwei Liu, Chong Wang, Zhonghai Li, Yanlin Wang , et al. · 2025

Code generation with large language models (LLMs) is highly sensitive to token selection during decoding, particularly at decision points where uncertainty strongly affects program correctness. Conventional strategies such as greedy decodi…

Benchmarking and Enhancing LLM Agents in Localizing Linux Kernel Bugs Open

Zhimin Zhou, Zhiyong Huang, Yao He, Chong Wang, Jiajun Wang , et al. · 2025

The Linux kernel is a critical system, serving as the foundation for numerous systems. Bugs in the Linux kernel can cause serious consequences, affecting billions of users. Fault localization (FL), which aims at identifying the buggy code …

Code Copycat Conundrum: Demystifying Repetition in LLM-based Code Generation Open

Mingwei Liu, Juntao Li, Xueying Du, Qiuyuan Chen, Hong Hao , et al. · 2025

Despite recent advances in Large Language Models (LLMs) for code generation, the quality of LLM-generated code still faces significant challenges. One significant issue is code repetition, which refers to the model's tendency to generate s…

Ginsenoside Rg1 alleviates ochratoxin A-induced liver inflammation in ducklings: Involvement of intestinal microbiota modulation and the TLR4/NF-κB pathway inhibition Open

Shuangshuang Zhai, Xin Peng, Cheng Liu, Ran Zhang, Caijun Jin , et al. · 2025

LogiAgent: Automated Logical Testing for REST Systems with LLM-Based Multi-Agents Open

Ke Zhang, Chenxi Zhang, Chong Wang, Chi Zhang, Yadi Wu , et al. · 2025

Automated testing for REST APIs has become essential for ensuring the correctness and reliability of modern web services. While existing approaches primarily focus on detecting server crashes and error codes, they often overlook logical is…

Code Digital Twin: Empowering LLMs with Tacit Knowledge for Complex Software Development Open

Xin Peng, Chong Wang, Mingwei Liu, Yiling Lou, Yijian Wu · 2025

Recent advances in large language models (LLMs) have demonstrated strong capabilities in software engineering tasks, raising expectations of revolutionary productivity gains. However, enterprise software development is largely driven by in…

A Survey of Fuzzing Open-Source Operating Systems Open

Kun Hu, Qi-Cai Chen, Zhaogeng Lu, Wei Zhang, Bihuan Chen , et al. · 2025

Vulnerabilities in open-source operating systems (OSs) pose substantial security risks to software systems, making their detection crucial. While fuzzing has been an effective vulnerability detection technique in various domains, OS fuzzin…

Deep learning-based prediction of autoimmune diseases Open

Donghong Yang, Xin Peng, Senlin Zheng, Shenglan Peng · 2025

Autoimmune Diseases are a complex group of diseases caused by the immune system mistakenly attacking body tissues. Their etiology involves multiple factors such as genetics, environmental factors, and abnormalities in immune cells, making …

The Impact of Intelligent Delivery Systems and Automated Rail Logistics on the Efficiency and Safety of Clinical Item Transportation: A Observational Studies Open

Yi Li, Ping He, Xin Peng, Min Peng · 2025

This paper aims to establish an intelligent delivery system integrated with track logistics and explores its impact on the clinical transportation of goods. The study analyzed hospital delivery items before and after the implementation of …

Application Research of FPGA-DSP Architecture in Ship Radar Signal Processing Open

Hang Zhou, Yongchun Liu, Xin Peng, Han Zeng, W. Cui D. Lu · 2024

In view of the continuous improvement of maritime safety requirements, the demand for maritime radar signal processing system is increasing day by day. A ship radar Signal processing system based on Field-Programmable Gate Array (FPGA) and…

VMud: Detecting Recurring Vulnerabilities with Multiple Fixing Functions via Function Selection and Semantic Equivalent Statement Matching Open

Kaifeng Huang, Chenhao Lu, Yuhua Cao, Bihuan Chen, Xin Peng · 2024

Killing Two Birds with One Stone: Malicious Package Detection in NPM and PyPI using a Single Model of Malicious Behavior Sequence Open

J. S. Zhang, Kaifeng Huang, Yiheng Huang, Bihuan Chen, Ruisi Wang , et al. · 2024

Open source software (OSS) supply chain enlarges the attack surface of a software system, which makes package registries attractive targets for attacks. Recently, multiple package registries have received intensified attacks with malicious…

Semantic Alignment-Enhanced Code Translation via an LLM-Based Multi-Agent System Open

Zhiqiang Yuan, W.Y. Chen, Hanlin Wang, Kai Yu, Xin Peng , et al. · 2024

Code translation converts code from one programming language to another while maintaining its original functionality, which is crucial for software migration, system refactoring, and cross-platform development. Traditional rule-based metho…

Large Language Model-Based Agents for Software Engineering: A Survey Open

Junwei Liu, Kaixin Wang, Yixuan Chen, Xin Peng, Zhenpeng Chen , et al. · 2024

The recent advance in Large Language Models (LLMs) has shaped a new paradigm of AI agents, i.e., LLM-based agents. Compared to standalone LLMs, LLM-based agents substantially extend the versatility and expertise of LLMs by enhancing LLMs w…

Evaluating and Improving ChatGPT for Unit Test Generation Open

Zhiqiang Yuan, Mingwei Liu, Shiji Ding, Kaixin Wang, Yixuan Chen , et al. · 2024

Unit testing plays an essential role in detecting bugs in functionally-discrete program units (e.g., methods). Manually writing high-quality unit tests is time-consuming and laborious. Although the traditional techniques are able to genera…

Embryo injected with Ochratoxin A induced jejunum injury in ducklings by activating the TLR4 signaling pathway: Involvement of intestinal microbiota Open

Xin Peng, Hailu Fan, Jinhui Liu, Xiayu Jiang, Cheng Liu , et al. · 2024

Ochratoxin A (OTA) is a common mycotoxin that causes intestinal injury in humans and various animal species. OTA may lead to intestinal injury in offspring due to the maternal effect. The aim of this study was to investigate the mechanism …

Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG Open

Xueying Du, Geng Zheng, K J Wang, Jiayi Feng, Wentai Deng , et al. · 2024

Although LLMs have shown promising potential in vulnerability detection, this study reveals their limitations in distinguishing between vulnerable and similar-but-benign patched code (only 0.06 - 0.14 accuracy). It shows that LLMs struggle…

LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-based Code Completion Open

Chong Wang, Kaifeng Huang, Jian Zhang, Yebo Feng, Lyuye Zhang , et al. · 2024

Large language models (LLMs), pre-trained or fine-tuned on large code corpora, have shown effectiveness in generating code completions. However, in LLM-based code completion, LLMs may struggle to use correct and up-to-date Application Prog…

A general approach to enhance the survivability of backdoor attacks by decision path coupling Open

Yufei Zhao, Dingji Wang, Bihuan Chen, Ziqian Chen, Xin Peng · 2024

Backdoor attacks have been one of the emerging security threats to deep neural networks (DNNs), leading to serious consequences. One of the mainstream backdoor defenses is model reconstruction-based. Such defenses adopt model unlearning or…

Xin Peng YOU? Author Swipe