Prompt-Enabled Large AI Models for CSI Feedback
Top Cited Papers
- 12 December 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 44 (07338716) , 2654-2668
Abstract
Artificial intelligence (AI) has emerged as a promising tool for channel state information (CSI) feedback. While recent research primarily focuses on improving feedback accuracy on a specific dataset through novel architectures, the underlying mechanism of AI-based CSI feedback remains unclear. This study explores the mechanism through analyzing performance across diverse datasets, with findings suggesting that superior feedback performance stems from AI models’ strong fitting capabilities and their ability to leverage environmental knowledge. Building on these findings, we propose a prompt-enabled large AI model (LAM) for CSI feedback. The LAM employs powerful Transformer blocks and is trained on extensive datasets from various scenarios. Meanwhile, the channel distribution (environmental knowledge), represented as the mean of channel magnitude in the angular-delay domain, is incorporated as a scenario-specific prompt within the decoder to further enhance reconstruction quality. Simulation results confirm that the proposed prompt-enabled LAM significantly improves feedback accuracy and generalization performance while reducing data collection requirements in new scenarios.Keywords
All Related Versions
Funding Information
- Key Technologies Research and Development Program of Jiangsu (BE2023022-1)
- Key Technologies Research and Development Program of Jiangsu (BE2023022)
- National Natural Science Foundation of China (62261160576)
- National Natural Science Foundation of China (62401640)
- Fundamental Research Funds for the Central Universities (2242023K5003)
- xGuangdong Basic and Applied Basic Research Foundation (2023A1515110732)
- Big Data Computing Center of Southeast University
- Center for Fundamental and Interdisciplinary Sciences of Southeast University
- National Science and Technology Council (NSTC 114-2221-E-110-031-MY3)
This publication has 42 references indexed in Scilit:
- WiFo: wireless foundation model for channel predictionScience China Information Sciences, 2025
- Explaining neural scaling lawsProceedings of the National Academy of Sciences of the United States of America, 2024
- Digital Twin Aided Massive MIMO: CSI Compression and Feedback2024
- A Tutorial on Extremely Large-Scale MIMO for 6G: Fundamentals, Signal Processing, and ApplicationsIEEE Communications Surveys & Tutorials, 2024
- Automated Environment-Aware Channel Feedback for 6G Massive MIMO Systems2023
- Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open IssuesIEEE Communications Surveys & Tutorials, 2023
- Accelerating and Compressing Deep Neural Networks for Massive MIMO CSI Feedback2023
- CSI-StripeFormer: Exploiting Stripe Features for CSI Compression in Massive MIMO System2023
- ChatGPT: five priorities for researchNature, 2023
- Four Generations of High-Dimensional Neural Network PotentialsChemical Reviews, 2021