While several benefits were realized for multilingual vision-language pretrained models, recent benchmarks across various tasks and languages showed poor cross-lingual generalisation when multilingually pre-trained vision-language models are applied to non-English data, with a large gap between (supervised) English performance and (zero-shot) cross-lingual transfer. In this work, we explore the poor performance of these models on a zero-shot cross-lingual visual question answering (VQA) task, where models are fine-tuned on English visual-question data and evaluated on 7 typologically diverse lResearch goal: What is the correlation between parameter scale (1B vs 7B vs 13B) and the effectiveness of English intermediate-task training for zero-shot cross-lingual transfer accuracy on multilingual visual question answering tasks?Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.8/10.