# Learnware for CSI Feedback: Scene-specific Small Models Can Do Big

arXiv: https://arxiv.org/abs/2608.17760 · HTML: https://mlsanity.com/paper/2608.17760/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 52 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Builds on (most cited first, 20 of 20)

- [The Benefit of Multitask Representation Learning](https://mlsanity.com/paper/1505.06279/) (2015)
- [Representation Similarity Analysis for Efficient Task taxonomy & Transfer Learning](https://mlsanity.com/paper/1904.11740/) (2019)
- [Toward a 6G AI-Native Air Interface](https://mlsanity.com/paper/2012.08285/) (2020)
- [Large Wireless Model (LWM): A Foundation Model for Wireless Channels](https://mlsanity.com/paper/2411.08872/) (2024)
- [Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems](https://mlsanity.com/paper/2206.14383/) (2022)
- [Learnware: Small Models Do Big](https://mlsanity.com/paper/2210.03647/) (2022)
- [Deep Learning-based Implicit CSI Feedback in Massive MIMO](https://mlsanity.com/paper/2105.10100/) (2021)
- [Beimingwu: A Learnware Dock System](https://mlsanity.com/paper/2401.14427/) (2024)
- [Prompt-Enabled Large AI Models for CSI Feedback](https://mlsanity.com/paper/2501.10629/) (2025)
- [Large AI Models for Wireless Physical Layer](https://mlsanity.com/paper/2508.02314/) (2025)
- [Evaluation Metrics and Methods for Generative Models in the Wireless PHY Layer](https://mlsanity.com/paper/2408.00634/) (2024)
- [Channel Modeling Aided Dataset Generation for AI-Enabled CSI Feedback: Advances, Challenges, and Solutions](https://mlsanity.com/paper/2407.00896/) (2024)
- [AI Enlightens Wireless Communication: A Transformer Backbone for CSI Feedback](https://mlsanity.com/paper/2206.07949/) (2022)
- [Digital Twin Aided Massive MIMO: CSI Compression and Feedback](https://mlsanity.com/paper/2402.19434/) (2024)
- [Vector Quantization for Deep-Learning-Based CSI Feedback in Massive MIMO Systems](https://mlsanity.com/paper/2403.07355/) (2024)
- [A Tale of Two Mobile Generations: 5G-Advanced and 6G in 3GPP Release 20](https://mlsanity.com/paper/2506.11828/) (2025)
- [A Dataset Similarity Evaluation Framework for Wireless Communications and Sensing](https://mlsanity.com/paper/2412.05556/) (2024)
- [AI/ML Life Cycle Management for Interoperable AI Native RAN](https://mlsanity.com/paper/2507.18538/) (2025)
- [Zone-Specific CSI Feedback for Massive MIMO: A Situation-Aware Deep Learning Approach](https://mlsanity.com/paper/2401.07451/) (2024)
- [Deep Learning-Based CSI Feedback for XL-MIMO Systems in the Near-Field Domain](https://mlsanity.com/paper/2405.09053/) (2024)

## Abstract (arXiv)

Intelligent channel state information (CSI) feedback is essential for realizing the high capacity and spectral efficiency goals of future 6G systems, yet existing deep learning solutions face a trade-off between model generalization and scenario-specific performance. Large neural networks generalize well but incur high computational and tuning costs, while small models excel in particular environments but require repetitive costly end-to-end training for each base station (BS). To address these challenges, we introduce a model repository-based deployment framework in which a centralized AI data center maintains a catalog of scene-specific CSI models. The repository is enhanced with a Learnware-based framework, where each model is associated with a specification including semantic part (network architecture parameters) and statistical part (codeboo-fingerprint embeddings of training-data distributions). A BS submits only its local statistical specifications to retrieve the most relevant pre-trained model, enhancing data privacy by avoiding raw CSI transmission and drastically reducing retrieval latency and communication overhead. We further develop a data-driven search strategy that matches codebook fingerprints to model performance, achieving over 90% selection accuracy. In simulations, our scheme yields 18.8% and 57.7% performance improvements over the General Model in LOS and NLOS scenarios, respectively while reducing local fine-tuning by up to 1000 samples and 100 epochs. This Learnware-based approach minimizes redundant training, maximizes model reuse, and supports rapid,privacy-enhancing deployment of CSI feedback models.