Related papers: Towards Semantic Clone Detection via Probabilistic…
Semantic inpainting is the task of inferring missing pixels in an image given surrounding pixels and high level image semantics. Most semantic inpainting algorithms are deterministic: given an image with missing regions, a single inpainted…
The rise of large language models (LLMs) like ChatGPT has significantly improved automated code generation, enhancing software development efficiency. However, this introduces challenges in academia, particularly in distinguishing between…
The pixel-wise dense prediction tasks based on weakly supervisions currently use Class Attention Maps (CAM) to generate pseudo masks as ground-truth. However, the existing methods typically depend on the painstaking training modules, which…
Stochastic process discovery is concerned with deriving a model capable of reproducing the stochastic character of observed executions of a given process, stored in a log. This leads to an optimisation problem in which the model's parameter…
While large language models (LLMs) have demonstrated strong capability in structured prediction tasks such as semantic parsing, few amounts of research have explored the underlying mechanisms of their success. Our work studies different…
Automatic differentiation plays a prominent role in scientific computing and in modern machine learning, often in the context of powerful programming systems. The relation of the various embodiments of automatic differentiation to the…
Statistical Model Checking (SMC) is a trade-off between testing and formal verification. The core idea of the approach is to conduct some simulations of the system and verify if they satisfy some given property. In this paper we show that…
We present evidence that language models (LMs) of code can learn to represent the formal semantics of programs, despite being trained only to perform next-token prediction. Specifically, we train a Transformer model on a synthetic corpus of…
Determining semantic textual similarity is a core research subject in natural language processing. Since vector-based models for sentence representation often use shallow information, capturing accurate semantics is difficult. By contrast,…
In modern software ecosystems, 1-day vulnerabilities pose significant security risks due to extensive code reuse. Identifying vulnerable functions in target binaries alone is insufficient; it is also crucial to determine whether these…
Consistency, which refers to the capability of generating the same predictions for semantically similar contexts, is a highly desirable property for a sound language understanding model. Although recent pretrained language models (PLMs)…
Detection of semantic data types is a very crucial task in data science for automated data cleaning, schema matching, data discovery, semantic data type normalization and sensitive data identification. Existing methods include regular…
Weakly Supervised Semantic Segmentation (WSSS), which leverages image-level labels, has garnered significant attention due to its cost-effectiveness. The previous methods mainly strengthen the inter-class differences to avoid class semantic…
As large language models (LLMs) excel at code reasoning, a natural question arises: can an LLM execute programs (i.e., act as an interpreter) purely based on a programming language's formal semantics? If so, it will enable rapid prototyping…
Code clones, referring to identical or similar code fragments, have long posed challenges in classical programming, impacting software quality, maintainability, and scalability. However, their presence and characteristics in quantum…
Software systems are getting more complex as the system grows where maintaining such system is a primary concern for the industry. Code clone is one of the factors making software maintenance more difficult. It is a process of replicating…
Transformer networks such as CodeBERT already achieve outstanding results for code clone detection in benchmark datasets, so one could assume that this task has already been solved. However, code clone detection is not a trivial task.…
Large language models (LLMs) are increasingly used to generate software artifacts across many software engineering (SE) tasks, yet ensuring the semantic validity of these artifacts remains a fundamental challenge. Existing constrained…
Code cloning is not only assumed to inflate maintenance costs but also considered defect-prone as inconsistent changes to code duplicates can lead to unexpected behavior. Consequently, the identification of duplicated code, clone detection,…
Semantic textual similarity (STS) systems are designed to encode and evaluate the semantic similarity between words, phrases, sentences, and documents. One method for assessing the quality or authenticity of semantic information encoded in…