Multilingual Vision-Language Models, A Survey
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909038646657024 |
|---|---|
| author | Manea, Andrei-Alexandru Libovický, Jindřich |
| author_facet | Manea, Andrei-Alexandru Libovický, Jindřich |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22123 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multilingual Vision-Language Models, A Survey Manea, Andrei-Alexandru Libovický, Jindřich Computation and Language 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. |
| title | Multilingual Vision-Language Models, A Survey |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.22123 |