{"ID":2865210,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.22123","arxiv_id":"2509.22123","title":"Multilingual Vision-Language Models, A Survey","abstract":"This survey examines multilingual vision-language models that process text and images across languages. We review 33 models and 23 benchmarks, spanning encoder-only and generative architectures, and identify a key tension between language neutrality (consistent cross-lingual representations) and cultural awareness (adaptation to cultural contexts). Current training methods favor neutrality through contrastive learning, while cultural awareness depends on diverse data. Two-thirds of evaluation benchmarks use translation-based approaches prioritizing semantic consistency, though recent work incorporates culturally grounded content. We find discrepancies in cross-lingual capabilities and gaps between training objectives and evaluation goals.","short_abstract":"This survey examines multilingual vision-language models that process text and images across languages. We review 33 models and 23 benchmarks, spanning encoder-only and generative architectures, and identify a key tension between language neutrality (consistent cross-lingual representations) and cultural awareness (ada...","url_abs":"https://arxiv.org/abs/2509.22123","url_pdf":"https://arxiv.org/pdf/2509.22123v2","authors":"[\"Andrei-Alexandru Manea\",\"Jindřich Libovický\"]","published":"2025-09-26T09:46:13Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Language Model\"]","has_code":false}