Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{171652,
        author = {Sanika Kulkarni and Balaji Chaugule},
        title = {Frontiers of Multimodal Generative AI: Efficiency, Adaptability, and Real-World Applications},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {8},
        pages = {770-778},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=171652},
        abstract = {Generative AI has revolutionized machine learning by enabling machines to create meaningful content across diverse modalities. The advent of multi-modal models, such as GPT-4 and CLIP, has expanded the boundaries of generative AI to address complex problems requiring nuanced understanding of multiple data types. This review focuses on four critical areas: Cross-Platform Adaptability, highlighting challenges and solutions in deploying multi-modal models across diverse hardware environments; Integration of Novel Modalities, discussing the incorporation of underexplored modalities such as bio-signals and haptics; Resource Efficiency and Sustainability, emphasizing energy-efficient strategies for model training and deployment; and Real-Time Applications, exploring the potential and challenges of multi-modal generative AI in dynamic environments like AR/VR and live translation. The paper synthesizes existing literature to identify progress, gaps, and future research directions, offering insights into making multi-modal generative AI more adaptable, efficient, and practical.},
        keywords = {Generative AI, Federated learning, GPT, Pruning, ChatGPT, Diffusion Model, Transformer, GAN, Artificial Intelligence, Quantization},
        month = {January},
        }