4 papers
Automated and Complete Generation of Traffic Scenarios at Road Junctions Using a Multi-level Danger Definition
Aren A. Babikian, Attila Ficsor, Oszkár Semeráth +2
To ensure their safe use, autonomous vehicles (AVs) must meet rigorous certification criteria that involve executing maneuvers safely within (arbitrary) scenarios where other actor…
ALPINE: An adaptive language-agnostic pruning method for language models for code
Mootez Saad, José Antonio Hernández López, Boqi Chen +2
Language models of code have demonstrated state-of-the-art performance across various software engineering and source code analysis tasks. However, their demanding computational re…
Certifying Robustness of Graph Convolutional Networks for Node Perturbation with Polyhedra Abstract Interpretation
Boqi Chen, Kristóf Marussy, Oszkár Semeráth +2
Graph convolutional neural networks (GCNs) are powerful tools for learning graph-based knowledge representations from training data. However, they are vulnerable to small perturbat…
On Inter-dataset Code Duplication and Data Leakage in Large Language Models
José Antonio Hernández López, Boqi Chen, Mootez Saaz +2
Motivation. Large language models (LLMs) have exhibited remarkable proficiency in diverse software engineering (SE) tasks. Handling such tasks typically involves acquiring foundati…