Kiana Shahrasbi

Cross-modal Associations in Vision and Language Models: Revisiting the Bouba-Kiki Effect

Recent advances in multimodal models have raised questions about whether vision-and-language models (VLMs) integrate cross-modal information in ways that reflect human cognition. One well-studied test case in this domain is the bouba-kiki effect, where humans reliably associate pseudowords like ‘bou…