Related papers: DeepCodeProbe: Towards Understanding What Models T…

In this paper, we investigate code-integrated reasoning, where models generate code when necessary and integrate feedback by executing it through a code interpreter. To acquire this capability, models must learn when and how to use external…

Does the training of large language models potentially infringe upon code licenses? Furthermore, are there any datasets available that can be safely used for training these models without violating such licenses? In our study, we assess the…

Deep Learning (DL) models have been widely used to support code completion. These models, once properly trained, can take as input an incomplete code component (e.g., an incomplete function) and predict the missing tokens to finalize it.…

Large Language Models (LLMs) and pre-trained Language Models (LMs) have achieved impressive success on many software engineering tasks (e.g., code completion and code generation). By leveraging huge existing code corpora (e.g., GitHub),…

In an ever expanding set of research and application areas, deep neural networks (DNNs) set the bar for algorithm performance. However, depending upon additional constraints such as processing power and execution time limits, or…

Over the past few years, deep learning methods have been applied for a wide range of Software Engineering (SE) tasks, including in particular for the important task of automatically predicting and localizing faults in software. With the…

As the potential for neural networks to augment our daily lives grows, ensuring their quality through effective testing, debugging, and maintenance is essential. This is especially the case as we acknowledge the prospects of negative…

In cognitive decoding, researchers aim to characterize a brain region's representations by identifying the cognitive states (e.g., accepting/rejecting a gamble) that can be identified from the region's activity. Deep learning (DL) methods…

Detecting code clones is relevant to software maintenance and code refactoring. This challenge still presents unresolved cases, mainly when structural similarity does not reflect functional equivalence, though recent code models show…

Code language models, while widely popular, are often trained on unsanitized source code gathered from across the Internet. Previous work revealed that pre-trained models can remember the content of their training data and regurgitate them…

Deep learning is a topic of considerable current interest. The availability of massive data collections and powerful software resources has led to an impressive amount of results in many application areas that reveal essential but hidden…

Semantic parsing is a technique aimed at constructing a structured representation of the meaning of a natural-language question. Recent advancements in few-shot language models trained on code have demonstrated superior performance in…

Machine Learning models increasingly face data integrity challenges due to the use of large-scale training datasets drawn from the Internet. We study what model developers can do if they detect that some data was manipulated or incorrect.…

Deep learning achieves remarkable performance on pattern recognition, but can be vulnerable to defects of some important properties such as robustness and security. This tutorial is based on a stream of research conducted since the summer…

Program semantics learning is the core and fundamental for various code intelligent tasks e.g., vulnerability detection, clone detection. A considerable amount of existing works propose diverse approaches to learn the program semantics for…

Pre-training a language model and then fine-tuning it has shown to be an efficient and effective technique for a wide range of code intelligence tasks, such as code generation, code summarization, and vulnerability detection. However,…

Large language models (LLMs) and transformer-based architectures are increasingly utilized for source code analysis. As software systems grow in complexity, integrating LLMs into code analysis workflows becomes essential for enhancing…

Machine learning algorithms are typically run on large scale, distributed compute infrastructure that routinely face a number of unavailabilities such as failures and temporary slowdowns. Adding redundant computations using coding-theoretic…

Visual quality inspection in high performance manufacturing can benefit from automation, due to cost savings and improved rigor. Deep learning techniques are the current state of the art for generic computer vision tasks like classification…

Large language models (LLMs) have demonstrated significant potential in the realm of natural language understanding and programming code processing tasks. Their capacity to comprehend and generate human-like code has spurred research into…