# RF-LEGO: Modularized Signal Processing-Deep Learning Co-Design for RF Sensing via Deep Unrolling

arXiv: https://arxiv.org/abs/2604.10183 · HTML: https://mlsanity.com/paper/2604.10183/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 75 references that are in the map.
- First posted on arXiv 11 Apr 2026.

## Builds on (most cited first, 29 of 29)

- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers](https://mlsanity.com/paper/2110.13985/) (2021)
- [PDE-Net: Learning PDEs from Data](https://mlsanity.com/paper/1710.09668/) (2017)
- [Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration](https://mlsanity.com/paper/1508.02848/) (2015)
- [KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics](https://mlsanity.com/paper/2107.10043/) (2021)
- [NeRF2: Neural Radio-Frequency Radiance Fields](https://mlsanity.com/paper/2305.06118/) (2023)
- [HARGPT: Are LLMs Zero-Shot Human Activity Recognizers?](https://mlsanity.com/paper/2403.02727/) (2024)
- [DeepSense 6G: A Large-Scale Real-World Multi-Modal Sensing and Communication Dataset](https://mlsanity.com/paper/2211.09769/) (2022)
- [SensorLM: Learning the Language of Wearable Sensors](https://mlsanity.com/paper/2506.09108/) (2025)
- [Deep Unfolded Robust PCA with Application to Clutter Suppression in Ultrasound](https://mlsanity.com/paper/1811.08252/) (2018)
- [RF-Diffusion: Radio Signal Generation via Time-Frequency Diffusion](https://mlsanity.com/paper/2404.09140/) (2024)
- [RAMP-CNN: A Novel Neural Network for Enhanced Automotive Radar Object Recognition](https://mlsanity.com/paper/2011.08981/) (2020)
- [RF-Net: a Unified Meta-learning Framework for RF-enabled One-shot Human Activity Recognition](https://mlsanity.com/paper/2111.04566/) (2021)
- [STFNets: Learning Sensing Signals from the Time-Frequency Perspective with Short-Time Fourier Neural Networks](https://mlsanity.com/paper/1902.07849/) (2019)
- [Towards Domain-Independent and Real-Time Gesture Recognition Using mmWave Signal](https://mlsanity.com/paper/2111.06195/) (2021)
- [CubeLearn: End-to-end Learning for Human Motion Recognition from Raw mmWave Radar Signals](https://mlsanity.com/paper/2111.03976/) (2021)
- [OPERAnet: A Multimodal Activity Recognition Dataset Acquired from Radio Frequency and Vision-based Sensors](https://mlsanity.com/paper/2110.04239/) (2021)
- [MoRe-Fi: Motion-robust and Fine-grained Respiration Monitoring via Deep-Learning UWB Radar](https://mlsanity.com/paper/2111.08195/) (2021)
- [Enabling Visual Recognition at Radio Frequency](https://mlsanity.com/paper/2405.19516/) (2024)
- [DA-MUSIC: Data-Driven DoA Estimation via Deep Augmented MUSIC Algorithm](https://mlsanity.com/paper/2109.10581/) (2021)
- [Wi-Chat: Large Language Model Powered Wi-Fi Sensing](https://mlsanity.com/paper/2502.12421/) (2025)
- [CFARnet: deep learning for target detection with constant false alarm rate](https://mlsanity.com/paper/2208.02474/) (2022)
- [RadioSES: mmWave-Based Audioradio Speech Enhancement and Separation System](https://mlsanity.com/paper/2204.07092/) (2022)
- [OpenRadar: A Toolkit for Prototyping mmWave Radar Applications](https://mlsanity.com/paper/1912.12395/) (2019)
- [USpeech: Ultrasound-Enhanced Speech with Minimal Human Effort via Cross-Modal Synthesis](https://mlsanity.com/paper/2410.22076/) (2024)
- [ASE: Practical Acoustic Speed Estimation Beyond Doppler via Sound Diffusion Field](https://mlsanity.com/paper/2412.20142/) (2024)
- [CFARNet: Learning-Based High-Resolution Multi-Target Detection for Rainbow Beam Radar](https://mlsanity.com/paper/2505.10150/) (2025)
- [Towards White-Box Deep Wireless Sensing](https://mlsanity.com/paper/2507.21799/) (2025)

## Abstract (arXiv)

Wireless sensing, traditionally relying on signal processing (SP) techniques, has recently shifted toward data-driven deep learning (DL) to achieve performance breakthroughs. However, existing deep wireless sensing models are typically end-to-end and task-specific, lacking reusability and interpretability. We propose RF-LEGO, a modular co-design framework that transforms interpretable SP algorithms into trainable, physics-grounded DL modules through deep unrolling. By replacing hand-tuned parameters with learnable ones while preserving core processing structures and mathematical operators, RF-LEGO ensures modularity, cascadability, and structure-aligned interpretability. Specifically, we introduce three deep-unrolled modules for critical RF sensing tasks: frequency transform, spatial angle estimation, and signal detection. Extensive experiments using real-world data for Wi-Fi, millimeter-wave, UWB, and 6G sensing demonstrate that RF-LEGO significantly outperforms existing SP and DL baselines, both standalone and when integrated into multiple downstream tasks. RF-LEGO pioneers a novel SP-DL co-design paradigm for wireless sensing via deep unrolling, shedding light on efficient and interpretable deep wireless sensing solutions. Our code is available at https://github.com/aiot-lab/RF-LEGO.