{"paper":{"title":"Maya: An Instruction Finetuned Multilingual Multimodal Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Abhipsha Das, Alham Fikri Aji, Anthony Susevski, Ashvanth.S, Bala Krishna S Vegesna, Chen Liu, Drishti Sharma, Genta Indra Winata, Isha Chaturvedi, Karthik Reddy Kanjula, Nahid Alam, Roshan Santhosh, Ryan Sze-Yin Chan, Shayekh Bin Islam, S M Iftekhar Uddin, Snegha A, Snehanshu Mukherjee, Surya Guthikonda, Timothy Chung","submitted_at":"2024-12-10T01:57:17Z","abstract_excerpt":"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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07112","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.07112/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}