# Design of a Standard-Compliant Real-Time Neural Receiver for 5G NR

arXiv: https://arxiv.org/abs/2409.02912 · HTML: https://mlsanity.com/paper/2409.02912/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Sep 2024.

## Built on by (most cited first, 12 of 12)

- [OTIS: Learning High-Quality Time Series Features With Tiny Encoders](https://mlsanity.com/paper/2410.07299/) (2024)
- [AutoBS: Autonomous Base Station Deployment with Reinforcement Learning and Digital Network Twins](https://mlsanity.com/paper/2502.19647/) (2025)
- [In-Context Learning for Gradient-Free Receiver Adaptation: Principles, Applications, and Theory](https://mlsanity.com/paper/2506.15176/) (2025)
- [ReQuestNet: A Foundational Learning model for Channel Estimation](https://mlsanity.com/paper/2508.08790/) (2025)
- [5G LDPC Linear Transformer for Channel Decoding](https://mlsanity.com/paper/2501.14102/) (2025)
- [Decoding for Punctured Convolutional and Turbo Codes: A Deep Learning Solution for Protocols Compliance](https://mlsanity.com/paper/2502.15475/) (2025)
- [End-to-End Human Pose Reconstruction from Wearable Sensors for 6G Extended Reality Systems](https://mlsanity.com/paper/2503.04860/) (2025)
- [Novel Deep Neural OFDM Receiver Architectures for LLR Estimation](https://mlsanity.com/paper/2503.20500/) (2025)
- [Transform-Invariant Generative Ray Path Sampling for Efficient Radio Propagation Modeling](https://mlsanity.com/paper/2603.01655/) (2026)
- [AI-RAN on NPUs: Baseband Processing Without Baseband Chips](https://mlsanity.com/paper/2607.04224/) (2026)
- [The OCUDU dApp Platform: An Open Runtime and E3 Interface for Real-Time AI-RAN](https://mlsanity.com/paper/2609.07843/) (2026)
- [Online Learning via Learned Latent Bayesian Tracking](https://mlsanity.com/paper/2609.31559/) (2026)

## Abstract (arXiv)

We detail the steps required to deploy a multi-user multiple-input multiple-output (MU-MIMO) neural receiver (NRX) in an actual cellular communication system. This raises several exciting research challenges, including the need for real-time inference and compatibility with the 5G NR standard. As the network configuration in a practical setup can change dynamically within milliseconds, we propose an adaptive NRX architecture capable of supporting dynamic modulation and coding scheme (MCS) configurations without the need for any re-training and without additional inference cost. We optimize the latency of the neural network (NN) architecture to achieve inference times of less than 1ms on an NVIDIA A100 GPU using the TensorRT inference library. These latency constraints effectively limit the size of the NN and we quantify the resulting signal-to-noise ratio (SNR) degradation as less than 0.7 dB when compared to a preliminary non-real-time NRX architecture. Finally, we explore the potential for site-specific adaptation of the receiver by investigating the required size of the training dataset and the number of fine-tuning iterations to optimize the NRX for specific radio environments using a ray tracing-based channel model. The resulting NRX is ready for deployment in a real-time 5G NR system and the source code including the TensorRT experiments is available online.