Information retrieval across different languages is an increasingly important challenge in natural language processing. Recent approaches based on multilingual pre-trained language models have achieved remarkable success, yet they often optimize for either monolingual, cross-lingual, or multilingual retrieval performance at the expense of others. This paper proposes a novel hybrid batch training strategy to simultaneously improve zero-shot retrieval performance across monolingual, cross-lingual, and multilingual settings while mitigating language bias. The approach fine-tunes multilingual langResearch goal: What is the impact of different batch composition strategies during training on the zero-shot retrieval performance of multilingual vision-language models across monolingual, cross-lingual, and multilingual settings as measured by recall@K on XTREME-R?Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.1/10.