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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Luo, Luqing, Gui, Wenjin, Liu, Yunfei, Zhang, Ziyue, Zhang, Yunxi, Wang, Fengxiang, Guo, Zonghao, Ma, Zizhi, Liu, Xinzhu, He, Hanxiang, Li, Jinhai, Qiu, Xin, Xie, Wupeng, Sun, Yangang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915464243838976
author Luo, Luqing
Gui, Wenjin
Liu, Yunfei
Zhang, Ziyue
Zhang, Yunxi
Wang, Fengxiang
Guo, Zonghao
Ma, Zizhi
Liu, Xinzhu
He, Hanxiang
Li, Jinhai
Qiu, Xin
Xie, Wupeng
Sun, Yangang
author_facet Luo, Luqing
Gui, Wenjin
Liu, Yunfei
Zhang, Ziyue
Zhang, Yunxi
Wang, Fengxiang
Guo, Zonghao
Ma, Zizhi
Liu, Xinzhu
He, Hanxiang
Li, Jinhai
Qiu, Xin
Xie, Wupeng
Sun, Yangang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18785
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EMind: A Foundation Model for Multi-task Electromagnetic Signals Understanding
Luo, Luqing
Gui, Wenjin
Liu, Yunfei
Zhang, Ziyue
Zhang, Yunxi
Wang, Fengxiang
Guo, Zonghao
Ma, Zizhi
Liu, Xinzhu
He, Hanxiang
Li, Jinhai
Qiu, Xin
Xie, Wupeng
Sun, Yangang
Signal Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
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.
title EMind: A Foundation Model for Multi-task Electromagnetic Signals Understanding
topic Signal Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.18785