Related papers: On Usefulness of the Deep-Learning-Based Bug Local…

Deep learning (DL) techniques are proven effective in many challenging tasks, and become widely-adopted in practice. However, previous work has shown that DL libraries, the basis of building and executing DL models, contain bugs and can…

As Deep Learning (DL) systems are widely deployed for mission-critical applications, debugging such systems becomes essential. Most existing works identify and repair suspicious neurons on the trained Deep Neural Network (DNN), which,…

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…

Deep learning, a branch of artificial intelligence, is a data-driven method that uses multiple layers of interconnected units or neurons to learn intricate patterns and representations directly from raw input data. Empowered by this…

Large language models are increasingly used for code generation and debugging, but their outputs can still contain bugs, that originate from training data. Distinguishing whether an LLM prefers correct code, or a familiar incorrect version…

Deep learning (DL) techniques are on the rise in the software engineering research community. More and more approaches have been developed on top of DL models, also due to the unprecedented amount of software-related data that can be used…

Researchers have developed numerous debugging approaches to help programmers in the debugging process, but these approaches are rarely used in practice. In this paper, we investigate how programmers debug their code and what researchers…

Bugs are essential in software engineering; many research studies in the past decades have been proposed to detect, localize, and repair bugs in software systems. Effectiveness evaluation of such techniques requires complex bugs, i.e.,…

Training a deep learning model on source code has gained significant traction recently. Since such models reason about vectors of numbers, source code needs to be converted to a code representation before vectorization. Numerous approaches…

As Deep Neural Networks (DNNs) are rapidly being adopted within large software systems, software developers are increasingly required to design, train, and deploy such models into the systems they develop. Consequently, testing and…

Transfer learning is a widely-used paradigm in deep learning, where models pre-trained on standard datasets can be efficiently adapted to downstream tasks. Typically, better pre-trained models yield better transfer results, suggesting that…

With the rapid development of large language models (LLMs), distributed training and inference frameworks like DeepSpeed have become essential for scaling model training and inference across multiple GPUs or nodes. However, the increasing…

The task of finding the best developer to fix a bug is called bug triage. Most of the existing approaches consider the bug triage task as a classification problem, however, classification is not appropriate when the sets of classes change…

Deep Learning applications are becoming increasingly popular. Developers of deep learning systems strive to write more efficient code. Deep learning systems are constantly evolving, imposing tighter development timelines and increasing…

Bug reports are common artefacts in software development. They serve as the main channel for users to communicate to developers information about the issues that they encounter when using released versions of software programs. In the…

Deep learning frameworks serve as the foundation for developing and deploying deep learning applications. To enhance the quality of deep learning frameworks, researchers have proposed numerous testing methods using deep learning models as…

Resolving bugs in the maintenance phase of software is a complicated task. Bug assignment is one of the main tasks for resolving bugs. Some Bugs cannot be fixed properly without making design decisions and have to be assigned to designers,…

Deep Learning (DL) models can be used to tackle time series analysis tasks with great success. However, the performance of DL models can degenerate rapidly if the data are not appropriately normalized. This issue is even more apparent when…

The unwavering success of deep learning in the past decade led to the increasing prevalence of deep learning methods in various application fields. However, the downsides of deep learning, most prominently its lack of trustworthiness, may…

Deep learning (DL) applications, built upon a heterogeneous and complex DL stack (e.g., Nvidia GPU, Linux, CUDA driver, Python runtime, and TensorFlow), are subject to software and hardware dependencies across the DL stack. One challenge in…