Related papers: From Code Smells to Best Practices: Tackling Resou…

Large language models (LLMs) have achieved remarkable progress in code generation, largely driven by the availability of high-quality code datasets for effective training. To further improve data quality, numerous training data optimization…

The rapid technological evolution has accelerated software development for various domains and use cases, contributing to a growing share of global carbon emissions. While recent large language models (LLMs) claim to assist developers in…

As new requirements are introduced and implemented in a software system, developers must identify the set of source code classes which need to be changed. Therefore, past effort has focused on predicting the set of classes impacted by a…

Enhancing reasoning capabilities remains a central focus in the LLM reasearch community. A promising direction involves requiring models to simulate code execution step-by-step to derive outputs for given inputs. However, as code is often…

The manual generation of test scripts is a time-intensive, costly, and error-prone process, indicating the value of automated solutions. Large Language Models (LLMs) have shown great promise in this domain, leveraging their extensive…

Large language models (LLMs) have achieved state-of-the-art performance in various software engineering tasks, including error detection, clone detection, and code translation, primarily leveraging high-resource programming languages like…

The Model Context Protocol (MCP) introduces a standard specification that defines how Foundation Model (FM)-based agents should interact with external systems by invoking tools. However, to understand a tool's purpose and features, FMs rely…

DL frameworks are the basis of constructing all DL programs and models, and thus their bugs could lead to the unexpected behaviors of any DL program or model relying on them. Such a wide effect demonstrates the necessity and importance of…

Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, watermarking enables reliable attribution and enhances the security of machine-generated…

A resource leak occurs when a program fails to release a finite resource like a socket, file descriptor or database connection. While sound static analysis tools can detect all leaks, automatically repairing them remains challenging. Prior…

With the increasing popularity of machine learning (ML), many open-source software (OSS) contributors are attracted to developing and adopting ML approaches. Comprehensive understanding of ML contributors is crucial for successful ML OSS…

The use of machine learning (ML) methods for prediction and forecasting has become widespread across the quantitative sciences. However, there are many known methodological pitfalls, including data leakage, in ML-based science. In this…

The ubiquity of smartphones, and their very broad capabilities and usage, make the security of these devices tremendously important. Unfortunately, despite all progress in security and privacy mechanisms, vulnerabilities continue to…

Accurate prediction of resource consumption and runtime for cloud workflow jobs is critical for scheduling efficiency, yet remains challenging due to the semi-structured nature of job configurations -- comprising shell commands,…

The rapid growth of language models, particularly in code generation, requires substantial computational resources, raising concerns about energy consumption and environmental impact. Optimizing language models inference resource…

Code smells and software vulnerabilities both increase maintenance cost, yet they are often handled by separate tools that miss structural context and produce noisy warnings. This paper presents The Code Whisperer, a hybrid framework that…

Build scripts automate the process of compiling source code, managing dependencies, running tests, and packaging software into deployable artifacts. These scripts are ubiquitous in modern software development pipelines for streamlining…

Training large language models (LLMs) in the cloud faces growing memory bottlenecks due to the limited capacity and high cost of GPUs. While GPU memory offloading to CPU and NVMe has made large-scale training more feasible, existing…

The safe deployment of large language models (LLMs) in high-stakes fields like biomedicine, requires them to be able to reason about cause and effect. We investigate this ability by testing 13 open-source LLMs on a fundamental task:…

Google's Machine Learning framework TensorFlow was open-sourced in November 2015 [1] and has since built a growing community around it. TensorFlow is supposed to be flexible for research purposes while also allowing its models to be…