Related papers: First-Class Variability Modeling in Matlab/Simulin…
Modular reasoning about class invariants is challenging in the presence of dependencies among collaborating objects that need to maintain global consistency. This paper presents semantic collaboration: a novel methodology to specify and…
Vision-Language-Action (VLA) models have recently emerged, demonstrating strong generalization in robotic scene understanding and manipulation. However, when confronted with long-horizon tasks that require defined goal states, such as LEGO…
Factor models are a very efficient way to describe high dimensional vectors of data in terms of a small number of common relevant factors. This problem, which is of fundamental importance in many disciplines, is usually reformulated in…
Modern software systems increasingly integrate machine learning (ML) due to its advancements and ability to enhance data-driven decision-making. However, this integration introduces significant challenges for software engineering,…
The dominant paradigm of monolithic scaling in Vision-Language Models (VLMs) is failing for understanding and reasoning in documents, yielding diminishing returns as it struggles with the inherent need of this domain for document-based…
Vision-language models (VLMs) allow to embed texts and images in a shared representation space. However, it has been shown that these models are subject to a modality gap phenomenon meaning there exists a clear separation between the…
Hybrid systems are characterized by the hybrid evolution of their state: A part of the state changes discretely, the other part changes continuously over time. Typically, modern control applications belong to this class of systems, where a…
Electrical power conversions are common in a large variety of engineering applications. With reference to AC/DC and DC/AC power conversions, a strong research interest resides in multilevel converters, thanks to the many advantages they…
The recently introduced weakly disentangled representations proposed to relax some constraints of the previous definitions of disentanglement, in exchange for more flexibility. However, at the moment, weak disentanglement can only be…
Hierarchically decomposed component-based system development reduces design complexity by supporting distribution of work and component reuse. For product line development, the variability of the components to be deployed in different…
If a modeling task is distributed, it will frequently be necessary to integrate models developed by different team members. Problems occur in the models integration step and particularly, in the comparison phase of the integration. This…
The use of Vision-Language Models (VLMs) in automated driving applications is becoming increasingly common, with the aim of leveraging their reasoning and generalisation capabilities to handle long tail scenarios. However, these models…
Visual deep learning (VDL) systems have shown significant success in real-world applications like image recognition, object detection, and autonomous driving. To evaluate the reliability of VDL, a mainstream approach is software testing,…
Transfer learning has recently become the dominant paradigm of machine learning. Pre-trained models fine-tuned for downstream tasks achieve better performance with fewer labelled examples. Nonetheless, it remains unclear how to develop…
Integrating large language models (LLMs) into autonomous driving has attracted significant attention with the hope of improving generalization and explainability. However, existing methods often focus on either driving or vision-language…
Vision-Language Models (VLMs) have demonstrated notable promise in autonomous driving by offering the potential for multimodal reasoning through pretraining on extensive image-text pairs. However, adapting these models from broad web-scale…
In industrial model-based development (MBD) frameworks, requirements are typically specified informally using textual descriptions. To enable the application of formal methods, these specifications need to be formalized in the input…
The Harland document management system implements a data model in which document (object) structure can be altered by mixin-style multiple inheritance at any time. This kind of structural fluidity has long been supported by knowledge-base…
Modelling the logical architecture of an automotive system as one central step in the development process leads to an early understanding of the fundamental functional properties of the system under design. This supports developers in…
The massive amount of current data has led to many different forms of data analysis processes that aim to explore this data to uncover valuable insights. Methodologies to guide the development of big data science projects, including…