Related papers: COMET: Coverage-guided Model Generation For Deep L…
Deep Learning (DL) frameworks play a critical role in advancing artificial intelligence, and their rapid growth underscores the need for a comprehensive understanding of software quality and maintainability. DL frameworks, like other…
Language models (LMs) built upon deep neural networks (DNNs) have recently demonstrated breakthrough effectiveness in software engineering tasks such as code generation, completion, and repair. This has paved the way for the emergence of…
Conventional continual pretraining (CPT) for large language model (LLM) domain adaptation often suffers from catastrophic forgetting and limited domain capacity. Existing strategies adopt layer expansion, introducing additional trainable…
Automatic unit test (UT) generation is essential for software quality assurance, but existing approaches--including symbolic execution, search-based approaches, and recent LLM-based generators--struggle to produce human-quality tests with…
Generative LLMs have been shown to effectively power AI-based code authoring tools that can suggest entire statements or blocks of code during code authoring. In this paper we present CodeCompose, an AI-assisted code authoring tool…
Deep-Learning(DL) applications have been widely employed to assist in various tasks. They are constructed based on a data-driven programming paradigm that is different from conventional software applications. Given the increasing popularity…
Large Language Models (LLMs) have training corpora containing large amounts of program code, greatly improving the model's code comprehension and generation capabilities. However, sound comprehensive research on detecting program…
Code completion is a key feature of Integrated Development Environments (IDEs), aimed at predicting the next tokens a developer is likely to write, helping them write code faster and with less effort. Modern code completion approaches are…
Innovation in the physical layer of communication systems has traditionally been achieved by breaking down the transceivers into sets of processing blocks, each optimized independently based on mathematical models. Conversely, deep learning…
Pre-trained language models (PLMs) have emerged as powerful tools for code understanding. However, deploying these PLMs in large-scale applications faces practical challenges due to their computational intensity and inference latency.…
Dead code introduces several challenges in software development, such as increased binary size and maintenance difficulties. It can also obscure logical errors and be exploited for obfuscation in malware. For LLM-based code-related tasks,…
Code vulnerability detection is crucial for ensuring the security and reliability of modern software systems. Recently, Large Language Models (LLMs) have shown promising capabilities in this domain. However, notable discrepancies in…
Based on its great successes in inference and denosing tasks, Dictionary Learning (DL) and its related sparse optimization formulations have garnered a lot of research interest. While most solutions have focused on single layer…
Deep Learning (DL) techniques for Natural Language Processing have been evolving remarkably fast. Recently, the DL advances in language modeling, machine translation and paragraph understanding are so prominent that the potential of DL in…
The increasing inclusion of Deep Learning (DL) models in safety-critical systems such as autonomous vehicles have led to the development of multiple model-based DL testing techniques. One common denominator of these testing techniques is…
We review and evaluate a body of deep learning knowledge tracing (DLKT) models with openly available and widely-used data sets, and with a novel data set of students learning to program. The evaluated knowledge tracing models include…
Large Language Models (LLMs) for code generation can replicate insecure patterns from their training data. To mitigate this, a common strategy for security hardening is to fine-tune models using supervision derived from the final…
Detecting bugs in Deep Learning (DL) libraries (e.g., TensorFlow/PyTorch) is critical for almost all downstream DL systems in ensuring effectiveness/safety for end users. Meanwhile, traditional fuzzing techniques can be hardly effective for…
Deep Learning (DL) models have rapidly advanced, focusing on achieving high performance through testing model accuracy and robustness. However, it is unclear whether DL projects, as software systems, are tested thoroughly or functionally…
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…