Gesina Schwalbe — accepted AI-conference papers

2026

Explaining, Verifying and Aligning Semantic Hierarchies in Vision-Language Model Embeddings

Gesina Schwalbe, Mert Keser, Moritz Bayerkuhnlein, Edgar Heinert, Annika Mütze, Marvin Keller +5

IJCAI 2026

Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image–text embedding space, yet the semantic organization of this space is rarely inspected. We present a post-hoc framework to explain, verify, and align the semantic hierarchies induc

Cited by 0 Scholar ↗

2026

Injecting Qualitative Spatial Reasoning into World Models via Logic Tensor Networks

Ajay Ramachandra, Gesina Schwalbe, Zoe Falomir

IJCAI 2026

World models (WM) learn predictive representations from high-dimensional sensory input. However, their internal knowledge is implicit and often inadequate for systematic reasoning about object structure. Qualitative Spatial Reasoning (QSR) models provide explicit human-readable object descriptions u

Cited by 0 Scholar ↗