# Semantic CSI Feedback for Beam Selection: When Task-Aware Embeddings from Sparse Pilots Outperform Full-Bandwidth Reconstruction

arXiv: https://arxiv.org/abs/2609.18368 · HTML: https://mlsanity.com/paper/2609.18368/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Builds on (most cited first, 10 of 10)

- [Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications](https://mlsanity.com/paper/2207.09353/) (2022)
- [DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications](https://mlsanity.com/paper/1902.06435/) (2019)
- [What is Semantic Communication? A View on Conveying Meaning in the Era of Machine Intelligence](https://mlsanity.com/paper/2110.00196/) (2021)
- [Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems](https://mlsanity.com/paper/2206.14383/) (2022)
- [Joint Source-Channel Coding: Fundamentals and Recent Progress in Practical Designs](https://mlsanity.com/paper/2409.17557/) (2024)
- [A Survey on Semantic Communication Networks: Architecture, Security, and Privacy](https://mlsanity.com/paper/2405.01221/) (2024)
- [Pruning the Pilots: Deep Learning-Based Pilot Design and Channel Estimation for MIMO-OFDM Systems](https://mlsanity.com/paper/2006.11796/) (2020)
- [Massive MIMO in 5G: How Beamforming, Codebooks, and Feedback Enable Larger Arrays](https://mlsanity.com/paper/2301.13390/) (2023)
- [Standalone and Non-Standalone Beam Management for 3GPP NR at mmWaves](https://mlsanity.com/paper/1805.04268/) (2018)
- [Transformer-assisted Parametric CSI Feedback for mmWave Massive MIMO Systems](https://mlsanity.com/paper/2410.06504/) (2024)

## Abstract (arXiv)

Classical CSI feedback in FDD massive MIMO transmits a compressed reconstruction of the channel, optimizing fidelity to the original signal regardless of the downstream task. We propose a semantic communication perspective: instead of reconstructing the channel, the UE transmits a learned semantic embedding optimized end-to-end for beam selection at the gNB. Comparing reconstruction-oriented feedback (CsiNet) against task-aware semantic feedback across two input domains and three observation scenarios, we show that a semantic embedding of just d=8 real values from only 43 NR CSI-RS pilots in the angular-delay domain achieves the highest beam prediction accuracy, outperforming every method with access to the full 512-subcarrier channel. The key insight is that beam-relevant information is intrinsically low-dimensional: the semantic encoder learns to discard reconstruction-irrelevant structure and retain only a compact representation that is relevant to beam selection, realizing the core principle of semantic communication: transmit the intent, not the signal.