TARU PUBLICATIONS
Journal of Information and Optimization Sciences cover
Hybrid ·Peer-reviewed·ISSN (Online): 2169-0103·ISSN (Print): 0252-2667

WoS  JIF 2026 : 0.4 (Q4)

Powered by:Powered by

Monthly Journal: Publishes theoretical and applied research on topics in information and optimization sciences.

Issues up to 2022 co-published with and available at:Taylor & Francis
submissions@tarupublications.com
Open Access Research Article

A comprehensive review of recent advances and future prospects of generative AI

, * , , , , ,

* Corresponding author · click or hover a name for details

pp. 205–211Vol. 46Issue 1January 2025DOI: 10.47974/JIOS-1864XML
Received:
07 Aug 2024
Published Online:
19 Feb 2025
Article type:
Research Article
Language:
EN
Article no.:
JIOS-1864
Pages:
205–211

Abstract

Generative AI has evolved rapidly and demonstrated accuracy in creating content with diverse yet too realistic styles. This paper provides a complete overview of the field, starting with its core principles and continuing with some recent results and potential future applications. This also covers requirements for new task-specific and data models, including our critical generative model generation (GANs, VAE, and more) in four image audio text videos. The paper emphasizes that generative AI has the potential to transform industries and lists some of these possible applications. It also reviews GAN technology limitations, including data bias, ethical questions, and model interpretability. To maximize the potential of this technology, we stress that it is crucial to construct reliable, interpretable, and self-sustainable generative models. The paper ends with a discussion of future directions, new trends in multimodal models, and scopes of energy-efficient approaches. Knowing the risks and potential ahead is how researchers and practitioners can make an informed choice to use generative AI for better or worse.

Keywords

Subject Classifications

68T05

References

[1] Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y., “Generative adversarial nets,” in Advances in Neural Information Processing Systems, pp. 2672-2680 (2014).
[2] A. Kapoor, S. Gupta, and J. Singh, “Applications of generative adversarial networks in healthcare: A comprehensive survey,” IEEE Access, vol. 11, pp. 12356–12370 (2023). doi: 10.1109/ACCESS.2023.3241236.
[3] M. Taylor, Y. Zhang, and S. Huang, “Generative AI in finance: Automated fraud detection and risk assessment,” IEEE Trans. FinTech, vol. 2, no. 1, pp. 45–57 (Mar. 2023). doi: 10.1109/TFT.2023.3285569.
[4] Kingma, D. P., and Welling, M., “Auto-encoding variational Bayes,” arXiv preprint arXiv:1312.6114 (2013).
[5] LeCun, Y., Bengio, Y., and Hinton, G., “Deep learning,” Nature, vol. 521, no. 7553, pp. 436-444 (2015).
[6] Buolamwini, J., and Gebru, T., “Gender shades: Intersectional accuracy disparities in commercial gender classification,” in Proceedings of the 1st Conference on Fairness, Accountability and Transparency, pp. 77-91 (2018).
[7] Ribeiro, M. T., Singh, S., and Guestrin, C., “Why should I trust you?: Explaining the predictions of any classifier,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135-1144 (2016).   
[8] Dinh, L., Sohl-Dickstein, J., and Bengio, S., “Density estimation using real NVP,” arXiv preprint arXiv:1605.08803 (2016).
[9] J. Ho, A. Jain, and P. Abbeel, “Denoising diffusion probabilistic models,” arXiv preprint arXiv:2006.11239 (2020). 
[10] K. Patel, N. Verma, and R. Desai, “Multimodal generative AI for virtual reality applications,” IEEE Trans. Multimedia, vol. 25, no. 7, pp. 1582–1591 (July 2023). doi: 10.1109/TMM.2023.3288110.
[11] L. Roberts, J. Matthews, and H. Chen, “Advancements in generative AI for drug discovery and design,” IEEE Trans. Comput. Biol. Bioinform., vol. 20, no. 5, pp. 782–790 (May 2023). doi: 10.1109/TCBB.2023.3278123.
[12] R. S. Kumar and G. Singh, “Generative AI models for content generation and anomaly detection in smart manufacturing,” IEEE Access, vol. 11, pp. 23112–23124 (2023). doi: 10.1109/ACCESS.2023.3274928.

Views: 555Downloads: 116Citations: 1