IQFM A Wireless Foundational Model for I/Q Streams in AI-Native 6G

TL;DR

This paper introduces IQFM, a pioneering raw IQ data foundational model for wireless communication tasks, achieving high accuracy with minimal labeled data and demonstrating strong generalization in AI-native 6G systems.

Contribution

IQFM is the first to develop a foundational model operating directly on raw IQ signals for multiple wireless tasks, utilizing a novel task-aware augmentation and contrastive SSL framework.

Findings

Achieves up to 99.67% accuracy in modulation classification with minimal labeled data.

Outperforms supervised baselines by up to 7x and 145x in key tasks.

Generalizes well to new tasks with limited samples and minimal fine-tuning.

Abstract

Foundational models have shown remarkable potential in natural language processing and computer vision, yet remain in their infancy in wireless communications. While a few efforts have explored image-based modalities such as channel state information (CSI) and frequency spectrograms, foundational models that operate directly on raw IQ data remain largely unexplored. This paper presents, IQFM, the first I/Q signal foundational model for wireless communications. IQFM supporting diverse tasks: modulation classification, angle-of-arrival (AoA), beam prediction, and RF fingerprinting, without heavy preprocessing or handcrafted features. We also introduce a task-aware augmentation strategy that categorizes transformations into core augmentations, such as cyclic time shifting, and task-specific augmentations. This strategy forms the basis for structured, task-dependent representation learning within a contrastive self-supervised learning (SSL) framework. Using this strategy, the lightweight encoder, pre-trained via SSL on over-the-air multi-antenna IQ data, achieves up to 99.67% and 65.45% accuracy on modulation and AoA classification, respectively, using only one labeled sample per class, outperforming supervised baselines by up to 7x and 145x. The model also generalizes to out-of-distribution tasks; when adapted to new tasks using only 500 samples per class and minimal parameter updates via LoRA, the same frozen encoder achieves 94.15% on beam prediction (vs. 89.53% supervised), 50.00% on RML2016a modulation classification (vs. 49.30%), and 96.05% on RF fingerprinting (vs. 96.64%). These results demonstrate the potential of raw IQ-based foundational models as efficient, reusable encoders for multi-task learning in AI-native 6G systems.