Skip to content
Preprint

Rethinking the Foundations of Two-Sided AI Models for 6G

Aug 2026 · 0 citations · 15 references
Engineering Computer Science Mathematics

TL;DR

This article integrates two-sided model processing into the 5G New Radio protocol stack and validate its operation alongside conventional NR on a real-world testbed, and presents gradient-free zeroth-order fine-tuning that requires only scalar feedback, facilitating multi-vendor interoperability.

Abstract

For next-generation air interfaces, two-sided artificial intelligence (AI) models have received growing attention, with AI models deployed at both the transmitter and receiver for efficient channel feedback and data communication. However, their practical deployment is complicated by assumptions commonly made in existing studies, including isolation from legacy users, training under predefined channel conditions, and gradient-based fine-tuning requiring substantial cross-vendor communication. This article revisits these assumptions and presents practical alternatives. First, for legacy coexistence, we integrate two-sided model processing into the 5G New Radio (NR) protocol stack and validate its operation alongside conventional NR on a real-world testbed. Second, instead of training under a massive number of predefined channel conditions, we construct a compact model table by jointly optimizing two-sided models with trainable surrogate channels, and select the best model according to the current channel condition to enable channel adaptation with high task performance and low training/storage overhead. Finally, unlike existing fine-tuning that exchanges large gradient vectors containing potentially private model information, we present gradient-free zeroth-order fine-tuning that requires only scalar feedback, facilitating multi-vendor interoperability. Together, these approaches advance the practical deployment of two-sided AI models while highlighting key open challenges.

View source

Similar papers

#artificial intelligence Review Sep 2026

Wireless Foundation Models: State-of-the-Art and Open Challenges

This analysis shows that current WFMs provide increasing evidence of reusable wireless representations, but this evidence varies considerably across task families and evaluation settings, and identifies open directions for improving data availability, evaluation rigor, generalization, efficient adaptation, and real-wor...

Alonso M. Pacheco Huachaca, J. J. Rodríguez Rodríguez, Ahmed Aboulfotouh et al. · 0 citations
#machine learning Preprint Oct 2026

Combining Improvements in Uplink AI-RAN

System-level performance results show that the combined AI features improve the mean uplink user throughput by roughly 27% compared to a non-AI baseline, confirming that the individual PHY and Medium Access Control AI features provide complementary gains when deployed jointly.

Petteri Kela, Dani Korpi, Mikko Honkala · 0 citations
2026

SysUM: NDT-Assisted System-Level Scenario-Adaptive Universal Model for AI-6G Networks

Existing works on artificial intelligence (AI)-empowered wireless communication primarily focus on monolithic usage scenarios and isolated tasks with limited labeled data or capacity-driven modular optimization, which become inadequate and unscalable with the proliferation of task classes and heterogeneous requirements...

Da-Zhi He, Tian-Yu Jiao, Tao Tao et al. · 0 citations
Preprint Sep 2026

On the Impact of Site-Specific Training for a Real-World 5G NR System

Site-specific training can improve wireless receiver performance without increasing computational complexity. However, real-world results have so far focused on fully trainable neural receivers and single-layer transmissions. We study site-specific finetuning of three receiver architectures: fully trainable neural, mod...

Reinhard Wiesmayr, Nuri Berke Baytekin, Chris Dick et al. · 1 citation
Review Aug 2026

6G communications: empowering the future with advanced AI and ML techniques

A unified view of how 6G communications, empowered by advanced AI and ML technologies and distributed intelligence, are expected to drive evolution and expedite the journey toward a smart and intelligent connected world is offered.

Jamal Hussain Arman, Fazal Muhammad, Muhammad Abdullah et al. · 0 citations

Optimized deep learning architectures for radio intelligence in 6G networks

The transition from Fifth Generation of Cellular Networks (5G) and 5G-Advanced toward Sixth-Generation Mobile Networks (6G) is redefining wireless communication systems as Artificial Intelligence (AI)-native infrastructures, where intelligence is embedded throughout the communication architecture and pushed closer to t...

Germán David Góez-Sánchez · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.