Maya: An Instruction Finetuned Multilingual Multimodal Model

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 lac...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-12
Hauptverfasser:	Alam, Nahid, Karthik Reddy Kanjula, Guthikonda, Surya, Chung, Timothy, Bala Krishna S Vegesna, Das, Abhipsha, Susevski, Anthony, Chan, Ryan Sze-Yin, Iftekhar Uddin, S M, Shayekh Bin Islam, Roshan Santhosh, Snegha, A, Sharma, Drishti, Liu, Chen, Chaturvedi, Isha, Genta Indra Winata, Ashvanth, S, Mukherjee, Snehanshu, Aji, Alham Fikri
Format:	Artikel
Sprache:	eng
Schlagworte:	Datasets Languages Toxicity
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!