EMind: A Foundation Model for Multi-task Electromagnetic Signals Understanding

TL;DR

EMind is a large-scale foundation model for electromagnetic signals that leverages physical properties and a unified dataset to enable cross-task generalization and efficient multi-source signal understanding.

Contribution

This work introduces EMind, the first unified electromagnetic signals foundation model, with a large standardized dataset and novel training strategies for multi-task learning.

Findings

EMind achieves strong performance across multiple downstream tasks.

The model demonstrates broad generalization capabilities.

Efficient learning from heterogeneous multi-source signals is enabled.

Abstract

Deep understanding of electromagnetic signals is fundamental to dynamic spectrum management, intelligent transportation, autonomous driving and unmanned vehicle perception. The field faces challenges because electromagnetic signals differ greatly from text and images, showing high heterogeneity, strong background noise and complex joint time frequency structure, which prevents existing general models from direct use. Electromagnetic communication and sensing tasks are diverse, current methods lack cross task generalization and transfer efficiency, and the scarcity of large high quality datasets blocks the creation of a truly general multitask learning framework. To overcome these issue, we introduce EMind, an electromagnetic signals foundation model that bridges large scale pretraining and the unique nature of this modality. We build the first unified and largest standardized electromagnetic signal dataset covering multiple signal types and tasks. By exploiting the physical properties of electromagnetic signals, we devise a length adaptive multi-signal packing method and a hardware-aware training strategy that enable efficient use and representation learning from heterogeneous multi-source signals. Experiments show that EMind achieves strong performance and broad generalization across many downstream tasks, moving decisively from task specific models to a unified framework for electromagnetic intelligence. The code is available at: https://github.com/GabrielleTse/EMind.