Improved Alignment of Modalities in Large Vision Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910892572016640 |
|---|---|
| author | Jangra, Kartik Singh, Aman Kumar Mann, Yashwani Rathee, Geetanjali |
| author_facet | Jangra, Kartik Singh, Aman Kumar Mann, Yashwani Rathee, Geetanjali |
| contents | Recent advancements in vision-language models have achieved remarkable results in making language models understand vision inputs. However, a unified approach to align these models across diverse tasks such as image captioning and visual question answering remains a challenge. Existing methods either require very big language models or very big datasets which is not efficient in utilizing existing models. This paper addresses this gap and devises a training strategy of auto-regressive vision-language models, to unify vision-language tasks like image-captioning and visual question answering. We propose four training stages for aligning the vision model with the language model, in other words, the language model is given an ability to process visual inputs. We also devise different attention masks for training transformer-based language models that improve the quality of visual features. Further, we introduce some findings, 1) the attention mask should not be applied on visual inputs, 2) the Language model converges faster on AI- generated data, 3) More work should be done in the alignment stage during the pre-training of the model, 4) the model can easily adapt to any downstream tasks like visual question answering on healthcare datasets like PathVQA. After training the model for one epoch for all the stages, it outperforms large models like VILA-13 billion models on common benchmarks like CIDEr scores on COCO and Flickr30k datasets and achieves very close scores to GIT-2 on the same dataset despite being a much smaller model trained on a much smaller dataset. All of the training is done using best practices available like multi- GPU parallel training, lower-precision training with 16-bit float numbers, faster attention (SDPA), and gradient accumulation, and completed the training within 12 hours. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_19508 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improved Alignment of Modalities in Large Vision Language Models Jangra, Kartik Singh, Aman Kumar Mann, Yashwani Rathee, Geetanjali Computer Vision and Pattern Recognition Machine Learning Recent advancements in vision-language models have achieved remarkable results in making language models understand vision inputs. However, a unified approach to align these models across diverse tasks such as image captioning and visual question answering remains a challenge. Existing methods either require very big language models or very big datasets which is not efficient in utilizing existing models. This paper addresses this gap and devises a training strategy of auto-regressive vision-language models, to unify vision-language tasks like image-captioning and visual question answering. We propose four training stages for aligning the vision model with the language model, in other words, the language model is given an ability to process visual inputs. We also devise different attention masks for training transformer-based language models that improve the quality of visual features. Further, we introduce some findings, 1) the attention mask should not be applied on visual inputs, 2) the Language model converges faster on AI- generated data, 3) More work should be done in the alignment stage during the pre-training of the model, 4) the model can easily adapt to any downstream tasks like visual question answering on healthcare datasets like PathVQA. After training the model for one epoch for all the stages, it outperforms large models like VILA-13 billion models on common benchmarks like CIDEr scores on COCO and Flickr30k datasets and achieves very close scores to GIT-2 on the same dataset despite being a much smaller model trained on a much smaller dataset. All of the training is done using best practices available like multi- GPU parallel training, lower-precision training with 16-bit float numbers, faster attention (SDPA), and gradient accumulation, and completed the training within 12 hours. |
| title | Improved Alignment of Modalities in Large Vision Language Models |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2503.19508 |