Related papers: Automatically Generating Dockerfiles via Deep Lear…

In this paper, we present a framework to generate compilers for embedded domain-specific languages (EDSLs). This framework provides facilities to automatically generate the boilerplate code required for building DSL compilers on top of…

Large language models (LLMs) excel at generating code from natural language (NL) descriptions. However, the plain textual descriptions are inherently ambiguous and often fail to capture complex requirements like intricate system behaviors,…

Developers of Molecular Dynamics (MD) codes face significant challenges when adapting existing simulation packages to new hardware. In a continuously diversifying hardware landscape it becomes increasingly difficult for scientists to be…

This paper shows that further evaluation metrics during model training are needed to decide about its applicability in inference. As an example, a LayoutLM-based model is trained for token classification in documents. The documents are…

Domain experts are increasingly employing machine learning to solve their domain-specific problems. This article presents six key challenges that a domain expert faces in transforming their problem into a computational workflow, and then…

Many search systems work with large amounts of natural language data, e.g., search queries, user profiles, and documents. Building a successful search system requires a thorough understanding of textual data semantics, where deep learning…

This research focuses on transforming CVEs to hands-on educational lab for cybersecurity training. The study shows the practical application of CVEs by developing containerized lab environments- Docker to simulate real-world vulnerabilities…

Vectorization via Single Instruction, Multiple Data (SIMD) architectures is a cornerstone of high-performance computing. To fully exploit hardware potential, developers often resort to explicit vectorization using intrinsics, as…

With easier access to powerful compute resources, there is a growing trend in AI for software development to develop large language models (LLMs) to address a variety of programming tasks. Even LLMs applied to tasks from the…

Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code…

Training and deploying the large language models requires a large mount of computational resource because the language models contain billions of parameters and the text has thousands of tokens. Another problem is that the large language…

With the growing use of DevOps tools and frameworks, there is an increased need for tools and techniques that support more than code. The current state-of-the-art in static developer assistance for tools like Docker is limited to shallow…

Executing complex terminal tasks remains a significant challenge for open-weight LLMs, constrained by two fundamental limitations. First, high-fidelity, executable training environments are scarce: environments synthesized from real-world…

Deep reinforcement learning (DRL), leveraging Deep Learning (DL) in reinforcement learning, has shown significant potential in achieving human-level autonomy in a wide range of domains, including robotics, computer vision, and computer…

Automated documentation of programming source code is a challenging task with significant practical and scientific implications for the developer community. We present a large language model (LLM)-based application that developers can use…

Code comments play a prominent role in program comprehension activities. However, source code is not always documented and code and comments not always co-evolve. To deal with these issues, researchers have proposed techniques to…

Reproducing results in publications by distributing publicly available source code is becoming ever more popular. Given the difficulty of reproducing machine learning (ML) experiments, there have been significant efforts in reducing the…

Deep neural networks, despite their remarkable success, remain fundamentally limited in their ability to perform Continual Learning (CL). While most current methods aim to enhance the capabilities of a single model, Inspired by the…

Parsing is a fundamental building block in modern compilers, and for industrial programming languages, it is a surprisingly involved task. There are known approaches to generate parsers automatically, but the prevailing consensus is that…

Deep neural networks are widely used for classification. These deep models often suffer from a lack of interpretability -- they are particularly difficult to understand because of their non-linear nature. As a result, neural networks are…