{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/maya-an-instruction-finetuned-multilingual","title":"Maya: An Instruction Finetuned Multilingual Multimodal Model","arxiv_id":"2412.07112","date":"2024-12-10","proceeding":null,"authors":["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"],"abstract":"The rapid development of large Vision-Language Models (VLMs) has led to impressive results on academic benchmarks, primarily in widely spoken languages. However, significant gaps remain in the ability of current VLMs to handle low-resource languages and varied cultural contexts, largely due to a lack of high-quality, diverse, and safety-vetted data. Consequently, these models often struggle to understand low-resource languages and cultural nuances in a manner free from toxicity. To address these limitations, we introduce Maya, an open-source Multimodal Multilingual model. Our contributions are threefold: 1) a multilingual image-text pretraining dataset in eight languages, based on the LLaVA pretraining dataset; 2) a thorough analysis of toxicity within the LLaVA dataset, followed by the creation of a novel toxicity-free version across eight languages; and 3) 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.","url_abs":"https://arxiv.org/abs/2412.07112v1","url_pdf":"https://arxiv.org/pdf/2412.07112v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"maya-an-instruction-finetuned-multilingual","repo_url":"https://github.com/nahidalam/maya","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.07112","atlas_url":"https://app.syntology.ai/?focus=2412.07112","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}