Information Bottleneck Theory In Multimodal AI: Principles, Architectures, And Emerging Research Directions
Author :
Akanksha Aher, Swaraj Rasam, Dr. Jasbir Kaur, Ifrah KampooJourna Name:
International Journal of Science, Engineering and Technology Volume:
14 issue:3 Year:Volume-14-issue-3 Views : 209
Abstract:
Artificial intelligence today faces a fundamental challenge: modern AI systems are trained on enormous quantities of data, yet most of that data is irrelevant to the task at hand. The Information Bottleneck (IB) principle offers a powerful theoretical answer — it teaches AI to retain only what is genuinely useful for a task while discarding everything else. This survey examines how IB applies to multimodal foundation models that process images and text simultaneously, such as CLIP, BLIP-2, LLaVA, and Flamingo. We explain the theory in accessible terms, review how these models apply IB in practice, and discuss real-world benefits, applications, and open challenges. Our goal is to bridge information-theoretic foundations and engineering practice for the MCA research community.
APA:Akanksha Aher, Swaraj Rasam, Dr. Jasbir Kaur, Ifrah Kampoo. (Volume-14, Issue-3 -(Year-Volume-14-issue-3)). Information Bottleneck Theory In Multimodal AI: Principles, Architectures, And Emerging Research Directions. Retrieved from https://www.ijset.in/wp-content/uploads/IJSET_V14_issue3_445.pdf
Chicago:Akanksha Aher, Swaraj Rasam, Dr. Jasbir Kaur, Ifrah Kampoo. "Information Bottleneck Theory In Multimodal AI: Principles, Architectures, And Emerging Research Directions" Example, Volume-14-issue-3-Year-Volume-14-issue-3-2348-4098. https://www.ijset.in/wp-content/uploads/IJSET_V14_issue3_445.pdf.