Multimodal AI Innovations for Signal Processing

The field of Multimodal AI is rapidly transforming our approach to signal processing, offering innovative solutions and opportunities in handling complex multimedia data. As technologies evolve, the integration of various data modalities- such as audio, visual, and textual signals- becomes increasingly critical. Foundational models serve as comprehensive frameworks that uphold these advancements, enabling sophisticated interpretation and manipulation of multimedia content. Despite significant progress, challenges remain in effectively merging these diverse data streams to create seamless and intelligent applications. This necessitates a deeper investigation into the methodologies that underpin such transformative innovations.

This Research Topic is in collaboration with the IEEE-EURASIP Summer School on Signal Processing: From Foundational Models to Multimedia Signal Processing - A Deep Dive in Multimodal AI, organized by the University of Florence from September 21st to 26th, 2025, in San Vincenzo, Italy. Building upon the discussions and presentations from the Summer School, this topic aims to further extend and disseminate the interdisciplinary research, recent advances, and practical methodologies showcased during the event. By engaging a community of researchers who participated in or are inspired by the Summer School, we seek to foster ongoing collaboration and accelerate progress at the intersection of foundational models and multimedia signal processing.

This Research Topic aims to delve into the convergence of foundational models and multimedia signal processing. By focusing on areas such as deep learning architectures, cross-modal data fusion, and real-time processing algorithms, the goal is to explore both the theoretical underpinnings and practical implementations of multimodal AI systems. Key questions to be addressed include: How can foundational models be optimized for multimedia applications? What novel approaches can be developed to enhance model robustness and scalability? And how can these technologies be employed to improve real-world data processing capabilities?

This scope encompasses the theoretical and practical challenges in multimedia signal processing and their intersection with foundational models. Researchers are invited to contribute to, but not limited to, the following themes:

Development of novel algorithms for integrating multimodal data streams

Implementation of foundational models to improve multimedia content analysis

Optimization of AI architectures for efficient real-time signal processing

Cross-disciplinary approaches to enhance signal interpretation and usability

Case studies showcasing the application of multimodal AI in diverse multimedia contexts

Contributions are encouraged in various forms, including original research articles, reviews, mini-reviews and experimental studies. By advancing our understanding of these interconnected domains, this topic seeks to foster innovation that will ultimately shape the future of signal processing in multimedia applications.

Article types and fees

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Community Case Study
• Conceptual Analysis
• Data Report
• Editorial
• FAIR² Data
• Hypothesis and Theory
• Methods
• Mini Review
• ... View all formats

Articles that are accepted for publication by our external editors following rigorous peer review incur a publishing fee charged to Authors, institutions, or funders.

Article types

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Community Case Study
• Conceptual Analysis
• Data Report
• Editorial
• FAIR² Data
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• Review
• Systematic Review
• Technology and Code

Keywords: Multimodal AI, foundational models, signal processing, multimedia applications, deep learning architectures, cross-modal data fusion, real-time processing

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.