Shakti-VLMs: Scalable Vision-Language Models for Enterprise AI
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_ | 1866911215588999168 |
|---|---|
| author | Shakhadri, Syed Abdul Gaffar KR, Kruthika Angadi, Kartik Basavaraj |
| author_facet | Shakhadri, Syed Abdul Gaffar KR, Kruthika Angadi, Kartik Basavaraj |
| contents | We introduce Shakti VLM, a family of vision-language models in the capacity of 1B and 4B parameters designed to address data efficiency challenges in multimodal learning. While recent VLMs achieve strong performance through extensive training data, Shakti models leverage architectural innovations to attain competitive results with fewer tokens. Key advancements include QK-Normalization for attention stability, hybrid normalization techniques, and enhanced positional encoding. A three-stage training strategy further optimizes learning efficiency. Evaluations show that Shakti-Shakti-VLM-1B and Shakti-VLM-4B excel in document understanding, Visual Reasoning, OCR extraction, and general multimodal reasoning. Our results highlight that high performance can be achieved through model design and training strategy rather than sheer data volume, making Shakti an efficient solution for enterprise-scale multimodal tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_17092 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Shakti-VLMs: Scalable Vision-Language Models for Enterprise AI Shakhadri, Syed Abdul Gaffar KR, Kruthika Angadi, Kartik Basavaraj Computer Vision and Pattern Recognition Computation and Language We introduce Shakti VLM, a family of vision-language models in the capacity of 1B and 4B parameters designed to address data efficiency challenges in multimodal learning. While recent VLMs achieve strong performance through extensive training data, Shakti models leverage architectural innovations to attain competitive results with fewer tokens. Key advancements include QK-Normalization for attention stability, hybrid normalization techniques, and enhanced positional encoding. A three-stage training strategy further optimizes learning efficiency. Evaluations show that Shakti-Shakti-VLM-1B and Shakti-VLM-4B excel in document understanding, Visual Reasoning, OCR extraction, and general multimodal reasoning. Our results highlight that high performance can be achieved through model design and training strategy rather than sheer data volume, making Shakti an efficient solution for enterprise-scale multimodal tasks. |
| title | Shakti-VLMs: Scalable Vision-Language Models for Enterprise AI |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2502.17092 |