# SpectrumFM: A Foundation Model for Intelligent Spectrum Management

arXiv: https://arxiv.org/abs/2505.06256 · HTML: https://mlsanity.com/paper/2505.06256/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 56 references that are in the map.
- First posted on arXiv 2 May 2025.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [SpectralGPT: Spectral Remote Sensing Foundation Model](https://mlsanity.com/paper/2311.07113/) (2023)
- [A Unified Sequence Interface for Vision Tasks](https://mlsanity.com/paper/2206.07669/) (2022)
- [Over the Air Deep Learning Based Radio Signal Classification](https://mlsanity.com/paper/1712.04578/) (2017)
- [Convolutional Radio Modulation Recognition Networks](https://mlsanity.com/paper/1602.04105/) (2016)
- [WirelessGPT: A Generative Pre-trained Multi-task Learning Framework for Wireless Communication](https://mlsanity.com/paper/2502.06877/) (2025)
- [Real-Time Radio Technology and Modulation Classification via an LSTM Auto-Encoder](https://mlsanity.com/paper/2011.08295/) (2020)
- [Deep Neural Network Architectures for Modulation Classification](https://mlsanity.com/paper/1712.00443/) (2017)
- [Deep Learning for Spectrum Sensing](https://mlsanity.com/paper/1909.02730/) (2019)
- [A Causality-aware Paradigm for Evaluating Creativity of Multimodal Large Language Models](https://mlsanity.com/paper/2501.15147/) (2025)
- [AMC-Net: An Effective Network for Automatic Modulation Classification](https://mlsanity.com/paper/2304.00445/) (2023)
- [A Novel Automatic Modulation Classification Scheme Based on Multi-Scale Networks](https://mlsanity.com/paper/2105.15037/) (2021)
- [SSwsrNet: A Semi-Supervised Few-Shot Learning Framework for Wireless Signal Recognition](https://mlsanity.com/paper/2404.02467/) (2024)
- [Joint Signal Detection and Automatic Modulation Classification via Deep Learning](https://mlsanity.com/paper/2405.00736/) (2024)
- [RIS-Enhanced Cognitive Integrated Sensing and Communication: Joint Beamforming and Spectrum Sensing](https://mlsanity.com/paper/2402.06879/) (2024)

## Built on by (most cited first, 6 of 6)

- [EMind: A Foundation Model for Multi-task Electromagnetic Signals Understanding](https://mlsanity.com/paper/2508.18785/) (2025)
- [A Multi-Modal Foundational Model for Wireless Communication and Sensing](https://mlsanity.com/paper/2602.04016/) (2026)
- [Scale What Counts, Mask What Matters: Evaluating Foundation Models for Zero-Shot Cross-Domain Wi-Fi Sensing](https://mlsanity.com/paper/2511.18792/) (2025)
- [When Does Multimodal AI Help? Diagnostic Complementarity of Vision-Language Models and CNNs for Spectrum Management in Satellite-Terrestrial Networks](https://mlsanity.com/paper/2604.03774/) (2026)
- [RFPrompt: Prompt-Based Expert Adaptation of the Large Wireless Model for Modulation Classification](https://mlsanity.com/paper/2605.03279/) (2026)
- [Wireless Foundation Models: State-of-the-Art and Open Challenges](https://mlsanity.com/paper/2609.04707/) (2026)

## Abstract (arXiv)

Intelligent spectrum management is crucial for improving spectrum efficiency and achieving secure utilization of spectrum resources. However, existing intelligent spectrum management methods, typically based on small-scale models, suffer from notable limitations in recognition accuracy, convergence speed, and generalization, particularly in the complex and dynamic spectrum environments. To address these challenges, this paper proposes a novel spectrum foundation model, termed SpectrumFM, establishing a new paradigm for spectrum management. SpectrumFM features an innovative encoder architecture that synergistically exploits the convolutional neural networks and the multi-head self-attention mechanisms to enhance feature extraction and enable robust representation learning. The model is pre-trained via two novel self-supervised learning tasks, namely masked reconstruction and next-slot signal prediction, which leverage large-scale in-phase and quadrature (IQ) data to achieve comprehensive and transferable spectrum representations. Furthermore, a parameter-efficient fine-tuning strategy is proposed to enable SpectrumFM to adapt to various downstream spectrum management tasks, including automatic modulation classification (AMC), wireless technology classification (WTC), spectrum sensing (SS), and anomaly detection (AD). Extensive experiments demonstrate that SpectrumFM achieves superior performance in terms of accuracy, robustness, adaptability, few-shot learning efficiency, and convergence speed, consistently outperforming conventional methods across multiple benchmarks. Specifically, SpectrumFM improves AMC accuracy by up to 12.1% and WTC accuracy by 9.3%, achieves an area under the curve (AUC) of 0.97 in SS at -4 dB signal-to-noise ratio (SNR), and enhances AD performance by over 10%.