M-MiniGPT4: Multilingual VLLM Alignment via Translated Data
This work addresses the problem of multilingual vision-language capabilities for low-resource and cross-lingual applications, representing an incremental improvement over existing methods.
The paper tackles multilingual vision-language understanding by developing M-MiniGPT4, a model that achieves 36% accuracy on the MMMU benchmark, outperforming state-of-the-art models in its weight class.
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.