WiFo-MiSAC: A Wireless Foundation Model for Multimodal Sensing and Communication Integration via Synesthesia of Machines (SoM)

TL;DR

WiFo-MiSAC is a versatile foundation model that unifies heterogeneous wireless signals for improved sensing and communication tasks through self-supervised learning and disentangled representations.

Contribution

It introduces a task-agnostic model with a shared-specific disentangled architecture for multimodal wireless data processing, enabling better generalization and integration.

Findings

Achieves state-of-the-art results in beam prediction and channel estimation.

Demonstrates robust few-shot adaptation to new modalities.

Facilitates seamless multimodal sensing and communication integration.

Abstract

Current learning-based wireless methods struggle with generalization due to the fragmented processing of communication and sensing data. WiFo-MiSAC addresses this as a task-agnostic foundation model that tokenizes heterogeneous signals into a unified space for self-supervised pre-training. A shared-specific disentangled mixture-of-experts (SS-DMoE) architecture is employed to decouple modality-shared and modality-specific representations, facilitating interaction without cross-modal interference. By combining masked reconstruction with contrastive alignment, the model achieves state-of-the-art performance across downstream tasks, including beam prediction and channel estimation. Experimental results demonstrate robust few-shot adaptation and seamless integration of new modalities, positioning WiFo-MiSAC as a scalable backbone for future integrated sensing and communication systems.