Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.07112 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913604262952960 |
|---|---|
| author | Alam, Nahid Kanjula, Karthik Reddy Guthikonda, Surya Chung, Timothy Vegesna, Bala Krishna S Das, Abhipsha Susevski, Anthony Chan, Ryan Sze-Yin Uddin, S M Iftekhar Islam, Shayekh Bin Santhosh, Roshan A, Snegha Sharma, Drishti Liu, Chen Chaturvedi, Isha Winata, Genta Indra S, Ashvanth. Mukherjee, Snehanshu Aji, Alham Fikri |
| author_facet | Alam, Nahid Kanjula, Karthik Reddy Guthikonda, Surya Chung, Timothy Vegesna, Bala Krishna S Das, Abhipsha Susevski, Anthony Chan, Ryan Sze-Yin Uddin, S M Iftekhar Islam, Shayekh Bin Santhosh, Roshan A, Snegha Sharma, Drishti Liu, Chen Chaturvedi, Isha Winata, Genta Indra S, Ashvanth. Mukherjee, Snehanshu Aji, Alham Fikri |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_07112 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Maya: An Instruction Finetuned Multilingual Multimodal Model Alam, Nahid Kanjula, Karthik Reddy Guthikonda, Surya Chung, Timothy Vegesna, Bala Krishna S Das, Abhipsha Susevski, Anthony Chan, Ryan Sze-Yin Uddin, S M Iftekhar Islam, Shayekh Bin Santhosh, Roshan A, Snegha Sharma, Drishti Liu, Chen Chaturvedi, Isha Winata, Genta Indra S, Ashvanth. Mukherjee, Snehanshu Aji, Alham Fikri Computer Vision and Pattern Recognition Computation and Language 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. |
| title | Maya: An Instruction Finetuned Multilingual Multimodal Model |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2412.07112 |