软件工程
Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, leading to their adoption in high-stakes domains such as healthcare, law, and scientific research. However, their reasoning often contains subtle logical…
Modern cloud architectures demand self-adaptive capabilities to manage dynamic operational conditions. Yet, existing solutions often impose centralized control models ill-suited to microservices decentralized nature. This paper presents…
[Context and Motivation] Global energy consumption has been steadily increasing in recent years, with data centers emerging as major contributors. This growth is largely driven by the widespread migration of applications to the Cloud,…
In this paper, we share our lessons learned from more than a decade of teaching software quality aspects within Software Engineering (SE) courses, where the focus is on Agile/Scrum settings: final year software development projects and the…
Kubernetes provides native autoscaling mechanisms, including the Horizontal Pod Autoscaler, Vertical Pod Autoscaler, and node-level autoscalers, to enable elastic resource management for cloud-native applications. However, production…
Early and accurate detection of gallbladder diseases is crucial, yet ultrasound interpretation is challenging. To address this, an AI-driven diagnostic software integrates our hybrid deep learning model MobResTaNet to classify ten…
Many recent research studies have focused on the well-being of software development team members, as this aspect may be critical not only for productivity and performance at work but also for the physical health and personal life of…
Code often suffers from performance bugs. These bugs necessitate the research and practice of code optimization. Traditional rule-based methods rely on manually designing and maintaining rules for specific performance bugs (e.g., redundant…
Compiler-based Control-Flow Integrity (CFI) offers strong forward-edge protection but remains challenging to deploy in large C/C++ software due to visibility mismatches, type inconsistencies, and unintended behavioral failures. We present…
Learning-based automated vulnerability repair (AVR) techniques that utilize fine-tuned language models have shown promise in generating vulnerability patches. However, questions remain about their ability to repair unseen vulnerabilities.…
Compilers are fundamental to modern software development, making the effective identification and resolution of compiler faults essential. However, localizing these faults to specific source files remains highly challenging due to the…
The issue localization task aims to identify the locations in a software repository that requires modification given a natural language issue description. This task is fundamental yet challenging in automated software engineering due to the…
Software issue resolution aims to address real-world issues in software repositories (e.g., bug fixing and efficiency optimization) based on natural language descriptions provided by users, representing a key aspect of software maintenance.…
In Text-to-SQL generation, large language models (LLMs) have shown strong generalization and adaptability. However, LLMs sometimes generate hallucinations, i.e.,unrealistic or illogical content, which leads to incorrect SQL queries and…
Autonomous vehicles rely on LiDAR based perception to support safety critical control functions such as adaptive cruise control and automatic emergency braking. While previous research has shown that LiDAR perception can be manipulated…
Automated program repair using neural models has shown promising results on benchmark datasets, yet practical deployment remains limited. In this study, we examine whether a small transformer model can meaningfully repair real-world Java…
Safety alignment can make frontier LMs overly conservative, degrading collaboration via hedging or false refusals. We present a lightweight toolkit with three parts: (1) Victor Calibration (VC), a multi-pass protocol that elicits a scalar…
Large language models (LLMs) are being increasingly adopted in the software engineering domain, yet the robustness of their grasp on core software design concepts remains unclear. We conduct an empirical study to systematically evaluate…
The growing complexity of log data in modern software systems has prompted the use of Large Language Models (LLMs) for automated log analysis. Current approaches typically rely on direct supervised fine-tuning (SFT) on log-label pairs.…
Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write/execute the actual code with minimal human intervention. Key to this process are agent manifests, configuration files…