3 papers
cs.AI2026
VERUS-LM: a Versatile Framework for Combining LLMs with Symbolic Reasoning
Benjamin Callewaert, Simon Vandevelde, Joost Vennekens
A recent approach to neurosymbolic reasoning is to explicitly combine the strengths of large language models (LLMs) and symbolic solvers to tackle complex reasoning tasks. However,…
cs.CV2024
Enhancing Computer Vision with Knowledge: a Rummikub Case Study
Simon Vandevelde, Laurent Mertens, Sverre Lauwers +1
Artificial Neural Networks excel at identifying individual components in an image. However, out-of-the-box, they do not manage to correctly integrate and interpret these components…
cs.LO2024
Efficiently grounding FOL using bit vectors
Lucas Van Laer, Simon Vandevelde, Joost Vennekens
Several paradigms for declarative problem solving start from a specification in a high-level language, which is then transformed to a low-level language, such as SAT or SMT. Often,…