Related papers: Array-Carrying Symbolic Execution for Function Con…

Formal specifications play a pivotal role in accurately characterizing program behaviors and ensuring software correctness. In recent years, leveraging large language models (LLMs) for the automatic generation of program specifications has…

The neural network has become an integral part of modern software systems. However, they still suffer from various problems, in particular, vulnerability to adversarial attacks. In this work, we present a novel program reasoning framework…

Task vectors offer a compelling mechanism for accelerating inference in in-context learning (ICL) by distilling task-specific information into a single, reusable representation. Despite their empirical success, the underlying principles…

While instruction cache analysis is essentially a solved problem, data cache analysis is more challenging. In contrast to instruction fetches, the data accesses generated by a memory instruction may vary with the program's inputs and across…

The translation of high-level abstract features into clear, and testable functional requirements (FRs) is a crucial step in software development, bridging the gap between user needs and technical specifications. In engineering practice,…

Feature Transformation (FT) is a core data-centric AI task that improves feature space quality to advance downstream predictive performance. However, discovering effective transformations remains challenging due to the large space of…

Code summary generation is the task of writing natural language descriptions of a section of source code. Recent advances in Large Language Models (LLMs) and other AI-based technologies have helped make automatic code summarization a…

Symbolic execution uses various algorithms (matching, (anti)unification), whose executions are parameters for proof object generation. This paper proposes a generic method for generating proof objects for such parameters. We present in…

People grasp flexible visual concepts from a few examples. We explore a neurosymbolic system that learns how to infer programs that capture visual concepts in a domain-general fashion. We introduce Template Programs: programmatic…

Event temporal graphs have been shown as convenient and effective representations of complex temporal relations between events in text. Recent studies, which employ pre-trained language models to auto-regressively generate linearised graphs…

Recent works have shown that Large Language Models (LLMs) could empower traditional neuro-symbolic models via programming capabilities to translate language into module descriptions, thus achieving strong visual reasoning results while…

Recently, a diverse set of decoding and reranking procedures have been shown effective for LLM-based code generation. However, a comprehensive framework that links and experimentally compares these methods is missing. We address this by…

This paper considers the problem of controller synthesis of signal temporal logic (STL) specifications for large-scale multi-agent systems, where the agents are dynamically coupled and subject to collaborative tasks. A compositional…

Reusing verification artefacts requires identifying structural and semantic similarities across programs and their specifications. In this paper, we focus on graph construction as a foundational step toward this goal. We present a pipeline…

Medical imaging research is increasingly shifting from controlled benchmark evaluation toward real-world clinical deployment. In such settings, applying analytical methods extends beyond model design to require dataset-aware workflow…

Prior works have demonstrated that implicit representations trained only for reconstruction tasks typically generate encodings that are not useful for semantic tasks. In this work, we propose a method that contextualises the encodings of…

Symbolic Execution is a formal method that can be used to verify the behavior of computer programs and detect software vulnerabilities. Compared to other testing methods such as fuzzing, Symbolic Execution has the advantage of providing…

Recent large language models (LLMs) achieve impressive performance in source-conditioned text generation but often fail to correctly provide fine-grained attributions for their outputs, undermining verifiability and trust. Moreover,…

Advances in logic programming and increasing industrial uptake of Datalog-inspired approaches demonstrate the emerging need to express powerful code analyses more easily. Declarative program analysis frameworks (e.g., using logic…

Code coverage is a widely used metric for quantifying the extent to which program elements, such as statements or branches, are executed during testing. Calculating code coverage is resource-intensive, requiring code building and execution…