# Edge-Efficient Transformer for End-to-End RF Spectrum Monitoring

arXiv: https://arxiv.org/abs/2607.18285 · HTML: https://mlsanity.com/paper/2607.18285/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [Over the Air Deep Learning Based Radio Signal Classification](https://mlsanity.com/paper/1712.04578/) (2017)
- [Transformers without Normalization](https://mlsanity.com/paper/2503.10622/) (2025)
- [Distributed Deep Learning Models for Wireless Signal Classification with Low-Cost Spectrum Sensors](https://mlsanity.com/paper/1707.08908/) (2017)
- [MB-TaylorFormer V2: Improved Multi-branch Linear Transformer Expanded by Taylor Formula for Image Restoration](https://mlsanity.com/paper/2501.04486/) (2025)
- [SimA: Simple Softmax-free Attention for Vision Transformers](https://mlsanity.com/paper/2206.08898/) (2022)
- [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 Based Automatic Modulation Recognition: Models, Datasets, and Challenges](https://mlsanity.com/paper/2207.09647/) (2022)

## Abstract (arXiv)

We present E-SpecFormer (Edge Spectrum monitoring Transformer) for end-to-end automatic modulation and covert channel (CC) recognition. We introduce LiTAN (Linear Tanh Attention Network), a Softmax- and LayerNorm-free attention mechanism that reduces complexity while increasing accuracy in RF tasks. E-SpecFormer is parameterized in four scalable variants (Nano, Small, Medium, Large) to accommodate diverse hardware constraints. Using the RadioML2018 dataset for modulation recognition, the Nano variant achieves 86.5% average accuracy for Signal-to-Noise Ratios (SNRs)>0 dB, and on the hardware Trojan (HT)-based CC dataset it reaches 94.2% accuracy, both with fewer than 10k parameters and up to speed of 92 μs per frame on FPGA/CPU co-execution, surpassing state-of-the-art edge models at a fraction of their cost. These results establish E-SpecFormer as an edge-efficient solution for real-time spectrum intelligence on Internet of Things (IoT) devices. GitHub link to the repository: https://github.com/zsniko/E-SpecFormer.