AI 中文总结
本研究提出基于隐式神经表示的无线基础模型WiFo-INR，通过两阶段自监督预训练实现高效紧凑的CSI表示，在性能提升的同时降低延迟，可高效迁移至多任务并实现零样本泛化。
AI 中文摘要
无线基础模型正成为面向AI的物理层设计的有前景范式。然而，现有方法通常将信道状态信息（CSI）建模为类图像的离散张量，采用通用令牌解码器，可能难以高效捕获复杂的高频变化，且常产生高维、与尺寸相关的表示。本文提出WiFo-INR，一种基于隐式神经表示（INR）的无线基础模型，将CSI表示为坐标条件神经函数。Transformer编码器将部分或粗略CSI映射为固定维调制令牌，适配基于SIREN的解码器；压缩自编码器支持量化CSI反馈。其采用两阶段自监督预训练方案：混合掩码与去噪改进信道重建，压缩增强预训练实现低压缩比下的准确CSI反馈。大量实验表明，WiFo-INR学习到高效、紧凑且与CSI尺寸无关的隐式无线表示；与现有基础模型相比，WiFo-INR提升了信道重建和CSI反馈性能，同时大幅降低推理延迟，还能以极少微调开销高效迁移至多种无线任务，并对未见CSI尺寸实现零样本泛化。
英文摘要
Wireless foundation models are emerging as a promising paradigm for AI-native physical-layer design. However, existing methods typically model channel state information (CSI) as image-like discrete tensors with generic token decoders that may struggle to capture complex high-frequency variations efficiently and often produce high-dimensional, size-dependent representations. In this paper, we propose WiFo-INR, an implicit neural representation (INR)-based wireless foundation model that represents CSI as a coordinate-conditioned neural function. A Transformer encoder maps partial or coarse CSI to fixed-dimensional modulation tokens that adapt a SIREN-based decoder, and a compression autoencoder enables quantized CSI feedback. It adopts a two-stage self-supervised pretraining scheme, where mixed masking and denoising improve channel reconstruction and compression-enhanced pretraining enables accurate CSI feedback at low compression ratios. Extensive experiments demonstrate that WiFo-INR learns efficient, compact, and CSI-size-independent implicit wireless representations. Compared with existing foundation models, WiFo-INR improves channel reconstruction and CSI feedback performance while substantially reducing inference latency. It also transfers efficiently to diverse wireless tasks with minimal fine-tuning overhead and achieves zero-shot generalization to unseen CSI sizes.
