Implementation Architectures and Systematic Survey of Multimodal Vision-Language Models

• Author(s): Niharika Patidar; Dr. Sachin Patel
• Paper ID: 1713739
• Page: 1783-1790
• Published Date: 23-01-2026
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 9 Issue 7 January-2026

Abstract

Social media has officially crossed the 5-billion-user mark, and we are on track to hit 6 billion within just a few years. Over 90% of teens and the majority of children now bypass text and photos in favor of fast-paced, short-form video. This shift has put immense pressure on platforms to keep up. When you?re dealing with millions of uploads every single day, traditional moderation tools which often look at data in silos just can?t keep pace with the nuance and context of modern content. To solve this, the industry is moving toward more sophisticated AI models, like Multimodal Large Language Models (MLLMs). These systems are designed to "think" more like humans by processing video, sound, and text simultaneously to catch harmful content that older models might miss. Implementing a service for filtering YouTube Shorts and Instagram Reels requires a sophisticated architectural design that balances information integrity with computational speed.

Citations

IRE Journals:
Niharika Patidar, Dr. Sachin Patel "Implementation Architectures and Systematic Survey of Multimodal Vision-Language Models" Iconic Research And Engineering Journals Volume 9 Issue 7 2026 Page 1783-1790 https://doi.org/10.64388/IREV9I7-1713739

IEEE:
Niharika Patidar, Dr. Sachin Patel "Implementation Architectures and Systematic Survey of Multimodal Vision-Language Models" Iconic Research And Engineering Journals, 9(7) https://doi.org/10.64388/IREV9I7-1713739