mlsanityData to 14 Oct 2026

Way to Build Native AI-driven 6G Air Interface: Principles, Roadmap, and Outlook

arXiv 2508.15277 ↗First posted 21 Aug 2025cs.IT cs.AI math.ITcited by 0

Not on the map. Why?

Abstract (arXiv)

Artificial intelligence (AI) is expected to serve as a foundational capability across the entire lifecycle of 6G networks, spanning design, deployment, and operation. This article proposes a native AI-driven air interface architecture built around two core characteristics: compression and adaptation. On one hand, compression enables the system to understand and extract essential semantic information from the source data, focusing on task relevance rather than symbol-level accuracy. On the other hand, adaptation allows the air interface to dynamically transmit semantic information across diverse tasks, data types, and channel conditions, ensuring scalability and robustness. This article first introduces the native AI-driven air interface architecture, then discusses representative enabling methodologies, followed by a case study on semantic communication in 6G non-terrestrial networks. Finally, it presents a forward-looking discussion on the future of native AI in 6G, outlining key challenges and research opportunities.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 59 of its 120 references that are in the map. First posted on arXiv 21 Aug 2025.

Builds on

59 of 120 references.

References · 59

  1. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  2. 2023A Survey of Large Language Modelscited by 2,576
  3. 2018Variational image compression with a scale hyperpriorcited by 935
  4. 2017The Perception-Distortion Tradeoffcited by 587
  5. 2017Opening the Black Box of Deep Neural Networks via Informationcited by 503
  6. 2020Deep Learning Enabled Semantic Communication Systemscited by 292
  7. 2023Language Modeling Is Compressioncited by 225
  8. 2019Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoffcited by 211
  9. 2020Nonlinear Transform Codingcited by 136
  10. 2019DeepJSCC-f: Deep Joint Source-Channel Coding of Images with Feedbackcited by 96
  11. 2021Nonlinear Transform Source-Channel Coding for Semantic Communicationscited by 76
  12. 2018Deep Learning for Joint Source-Channel Coding of Textcited by 69
38 more
  1. 2024Compression Represents Intelligence Linearlycited by 56
  2. 2020Toward a 6G AI-Native Air Interfacecited by 55
  3. 2022Wireless Deep Video Semantic Transmissioncited by 50
  4. 2023SwinJSCC: Taming Swin Transformer for Deep Joint Source-Channel Codingcited by 45
  5. 2022Deep Joint Source-Channel Coding for Semantic Communicationscited by 41
  6. 2022Overview of Deep Learning-based CSI Feedback in Massive MIMO Systemscited by 37
  7. 2022WITT: A Wireless Image Transmission Transformer for Semantic Communicationscited by 37
  8. 2023Deep Joint Source-Channel Coding for Adaptive Image Transmission over MIMO Channelscited by 28
  9. 2023White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?cited by 23
  10. 2023AI-Generated Incentive Mechanism and Full-Duplex Semantic Communications for Information Sharingcited by 21
  11. 2024Lossless data compression by large modelscited by 20
  12. 2023Joint Coding-Modulation for Digital Semantic Communications via Variational Autoencodercited by 18
  13. 2022Vector Quantized Semantic Communication Systemcited by 16
  14. 2022Imitation Learning-based Implicit Semantic-aware Communication Networks: Multi-layer Representation and Collaborative Reasoningcited by 16
  15. 2023Joint Source-Channel Coding for Channel-Adaptive Digital Semantic Communicationscited by 15
  16. 2020Deep Learning for Joint Channel Estimation and Feedback in Massive MIMO Systemscited by 14
  17. 2022Deep Joint Source-Channel Coding for CSI Feedback: An End-to-End Approachcited by 14
  18. 2023SCAN: Semantic Communication with Adaptive Channel Feedbackcited by 14
  19. 2023DeepMA: End-to-end Deep Multiple Access for Wireless Image Transmission in Semantic Communicationcited by 12
  20. 2024OFDM-Based Digital Semantic Communication with Importance Awarenesscited by 12
  21. 2023Knowledge Base Enabled Semantic Communication: A Generative Perspectivecited by 11
  22. 2019Deep Convolutional Compression for Massive MIMO CSI Feedbackcited by 9
  23. 2022Deep CSI Compression for Massive MIMO: A Self-information Model-driven Neural Networkcited by 9
  24. 2023Semantic-Forward Relaying: A Novel Framework Towards 6G Cooperative Communicationscited by 9
  25. 2024From Analog to Digital: Multi-Order Digital Joint Coding-Modulation for Semantic Communicationcited by 9
  26. 2024Robust Image Semantic Coding with Learnable CSI Fusion Masking over MIMO Fading Channelscited by 9
  27. 2022Toward Adaptive Semantic Communications: Efficient Data Transmission via Online Learned Nonlinear Transform Source-Channel Codingcited by 8
  28. 2021Rate Distortion Characteristic Modeling for Neural Image Compressioncited by 6
  29. 2022Wireless Deep Speech Semantic Transmissioncited by 6
  30. 2023Non-Orthogonal Multiple Access Enhanced Multi-User Semantic Communicationcited by 6
  31. 2024A Semantic-Aware Multiple Access Scheme for Distributed, Dynamic 6G-Based Applicationscited by 6
  32. 2024S-RAN: Semantic-Aware Radio Access Networkscited by 6
  33. 2024Digital Twin Channel for 6G: Concepts, Architectures and Potential Applicationscited by 5
  34. 2024Generative Semantic Communication: Architectures, Technologies, and Applicationscited by 5
  35. 2022The Internet of Senses: Building on Semantic Communications and Edge Intelligencecited by 4
  36. 2025ICDM: Interference Cancellation Diffusion Models for Wireless Semantic Communicationscited by 4
  37. 2025Synonymous Variational Inference for Perceptual Image Compressioncited by 4
  38. 2024Distributed Task-Oriented Communication Networks with Multimodal Semantic Relay and Edge Intelligencecited by 3

50 most cited of 59 All 59 (JSON)

Built on by

Not cited yet.