To support future intelligent multifunctional sixth-generation (6G) wireless communication networks,Synesthesia of Machines (SoM) is proposed as a novel paradigm for artificial intelligent(AI)-native intelligent multi-modal sensing-communication integration. However, existing SoM system designs rely on task-specific Al models and face challenges such as scarcity of massive high-quality datasets,constrained modeling capability, poor generalization, and limited universality. Recently,foundation models (FMs) have emerged as a new deep learning paradigm and have been preliminarily applied to SoM-related tasks, but a systematic design framework is still lacking. First, the report will introduce the basic concepts of SoM and systematically introduce two roadmaps for empowering SoM with LLM/foundation models, including large language models (LLMs), and SoM domain-specific FMs( Wireless Foundation Models). Second, the report will introduce the latest large-scale, high-fidelity intelligent multi-modal sensing-communication integration dataset SynthSoM, and focus on FM-empowered SoM transceivers based on this dataset, including LLM-based and wireless foundation model-based design.For LLM-based design, the report will propose LLM for path loss generation (LLM4PG), LLM for wireless multi-task SoM transceiver (LLM4WM).For wireless foundation model-based design, the report will introduce wireless foundation model (WiFo) for channel prediction. Additionally, the report will present the first hardware demo of a video transmission system embedded with a WiFo.