2 papers
cs.AI2026
Same Content, Different Answers: Cross-Modal Inconsistency in MLLMs
Angela van Sprang, Laurens Samson, Ana Lucic +3
We introduce two new benchmarks REST and REST+ (Render-Equivalence Stress Tests) to enable systematic evaluation of cross-modal inconsistency in multimodal large language models (M…
cs.LG2025
Interpretability for Time Series Transformers using A Concept Bottleneck Framework
Angela van Sprang, Erman Acar, Willem Zuidema
Mechanistic interpretability focuses on reverse engineering the internal mechanisms learned by neural networks. We extend our focus and propose to mechanistically forward engineer…