M-MiniGPT4: Multilingual VLLM Alignment via Translated Data
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910088455782400 |
|---|---|
| author | Han, Seung Hun Mohamed, Youssef Elhoseiny, Mohamed |
| author_facet | Han, Seung Hun Mohamed, Youssef Elhoseiny, Mohamed |
| contents | This paper presents a Multilingual Vision Large Language Model, named M-MiniGPT4. Our model exhibits strong vision-language understanding (VLU) capabilities across 11 languages. We utilize a mixture of native multilingual and translated data to push the multilingual VLU performance of the MiniGPT4 architecture. In addition, we propose a multilingual alignment training stage that uses parallel text corpora to further enhance the multilingual capabilities of our model. M-MiniGPT4 achieves 36% accuracy on the multilingual MMMU benchmark, outperforming state-of-the-art models in the same weight class, including foundation models released after the majority of this work was completed. We open-source our models, code, and translated datasets to facilitate future research in low-resource and multilingual settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_29467 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | M-MiniGPT4: Multilingual VLLM Alignment via Translated Data Han, Seung Hun Mohamed, Youssef Elhoseiny, Mohamed Computation and Language Artificial Intelligence This paper presents a Multilingual Vision Large Language Model, named M-MiniGPT4. Our model exhibits strong vision-language understanding (VLU) capabilities across 11 languages. We utilize a mixture of native multilingual and translated data to push the multilingual VLU performance of the MiniGPT4 architecture. In addition, we propose a multilingual alignment training stage that uses parallel text corpora to further enhance the multilingual capabilities of our model. M-MiniGPT4 achieves 36% accuracy on the multilingual MMMU benchmark, outperforming state-of-the-art models in the same weight class, including foundation models released after the majority of this work was completed. We open-source our models, code, and translated datasets to facilitate future research in low-resource and multilingual settings. |
| title | M-MiniGPT4: Multilingual VLLM Alignment via Translated Data |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2603.29467 |