Large AI Model for Multimodal Integrated Sensing and Communication

Multimodal integrated sensing and communication (ISAC) exploits heterogeneous modalities to enhance perception accuracy, communication robustness, and environmental adaptability, becoming a key enabler of the Internet of Everything (IoE). Nevertheless, existing multimodal ISAC systems remain constrained by heterogeneous data characteristics, dynamic modality availability, and the limited adaptability of current fusion strategies. To overcome these limitations, we propose a LAM-enabled multimodal ISAC (LAM-MSAC) framework. First, modality-specific feature encoders are introduced to provide native compatibility for diverse sensing data. Second, to cope with dynamically changing modality combinations, we design a Mixture-of-Experts (MoE) fusion module in which multiple experts process different modal combinations. Finally, the MoE structure activates only a subset of experts for each inference, substantially reducing computational cost without sacrificing model capacity. A case study shows that LAM-MSAC achieves over 90% beam prediction accuracy while significantly lowering computation compared with maintaining multiple single- or multi-modality models. Potential research directions are further discussed to advance the integration of LAMs into multimodal ISAC.