在Maya背後：構建多語言視覺語言模型

Behind Maya: Building a Multilingual Vision Language Model

May 13, 2025

作者: Nahid Alam, Karthik Reddy Kanjula, Surya Guthikonda, Timothy Chung, Bala Krishna S Vegesna, Abhipsha Das, Anthony Susevski, Ryan Sze-Yin Chan, S M Iftekhar Uddin, Shayekh Bin Islam, Roshan Santhosh, Snegha A, Drishti Sharma, Chen Liu, Isha Chaturvedi, Genta Indra Winata, Ashvanth. S, Snehanshu Mukherjee, Alham Fikri Aji

cs.AI

摘要

近年來，我們見證了大規模視覺-語言模型（VLMs）的快速發展。這些模型在學術基準測試中展現了令人印象深刻的成果，主要集中於廣泛使用的語言，但在低資源語言和多樣文化情境下的表現則有所不足。為解決這些限制，我們推出了Maya，一個開源的多語言視覺-語言模型。我們的主要貢獻包括：1）基於LLaVA預訓練數據集，構建了一個涵蓋八種語言的多語言圖像-文本預訓練數據集；以及2）支持這些語言的多語言圖像-文本模型，提升了視覺-語言任務中的文化與語言理解能力。代碼已開源於https://github.com/nahidalam/maya。

English

In recent times, we have seen a rapid development of large Vision-Language Models (VLMs). They have shown impressive results on academic benchmarks, primarily in widely spoken languages but lack performance on low-resource languages and varied cultural contexts. To address these limitations, we introduce Maya, an open-source Multilingual VLM. Our contributions are: 1) a multilingual image-text pretraining dataset in eight languages, based on the LLaVA pretraining dataset; and 2) a multilingual image-text model supporting these languages, enhancing cultural and linguistic comprehension in vision-language tasks. Code available at https://github.com/nahidalam/maya.