WiFo-2: a generalist foundation model unifies heterogeneous wireless system design

TL;DR

WiFo-2 is a versatile foundation model trained on extensive wireless data, enabling unified, accurate, and efficient wireless system design and sensing across diverse scenarios with minimal training data.

Contribution

The paper introduces WiFo-2, a generalist wireless foundation model trained on 11.6 billion CSI points, achieving zero-shot performance and reducing training data needs for multiple wireless tasks.

Findings

WiFo-2 outperforms task-specific models in zero-shot channel reconstruction.

Achieves state-of-the-art results with only 1% of supervised training samples.

Demonstrated real-world deployability with a hardware prototype.

Abstract

Emerging sixth-generation wireless systems are increasingly heterogeneous, with compatibility across diverse configurations, ubiquitous coverage, and expanded functionalities. Although deep learning has substantially benefited wireless system design, existing approaches are typically trained for specific system settings and scenarios with limited generalizability. Here we present WiFo-2, a space-time-frequency foundation model for unified wireless communications and sensing system design. Pretrained on a heterogeneous dataset of 11.6 billion channel state information (CSI) points, WiFo-2 learns generalized wireless representations across scenarios, configurations, and tasks, and exhibits scaling-law behavior. WiFo-2 achieves reliable and accurate zero-shot channel reconstruction, outperforming fully supervised task-specific models. With only 1% of the training samples required by supervised AI models, WiFo-2 achieves state-of-the-art performance across 9 distinct wireless tasks. A functional hardware prototype further demonstrates its real-world deployability and superior capability across diverse wireless tasks. This work provides a versatile wireless design framework and advances understanding of wireless channels.