arXiv cs.AI· Shrihari Vasudevan, H. G. Ranjani, Raaghul Ranganathan, Satwik Sahu, Thirumaran Ekambaram·· 12 小时前AI 评分20
超越信道数据：融合配置信息的无线基础模型预训练
Beyond Channel Data: Configuration-Enriched Radio Foundation Models
AI 导读
该论文提出将信道配置（CFG）信息引入无线基础模型（RFM）预训练，使生成的 CFG 增强嵌入在标签稀缺的下游任务中充当有效的归纳先验。在 LoS/NLoS 分类、定时提前（TA）估计和波束选择任务上，该方法在分布内与分布外配置场景中均持续优于或媲美原始信道 token 及多个基线模型。
正文 · 原文
Abstract:This paper proposes incorporating channel configuration (CFG) information into Radio Foundation Model (RFM) pre-training and demonstrates that the resulting CFG-enriched embeddings serve as effective inductive priors for downstream tasks under label scarcity. We compare the proposed embeddings with raw channel tokens and multiple baseline models, under three different data regimes, for multiple downstream tasks --- Line-of-Sight/Non-Line-of-Sight (LoS/NLoS) classification, timing advance (TA) estimation, and beam selection. Evaluation is done in both in-distribution and out-of-distribution configuration settings. Experimental outcomes show that the proposed embeddings consistently outperform and/or are competitive to the baselines, across experiments in both seen and unseen configuration scenarios.
| Comments: | Submitted to IEEE ICC 2027 for review |
| Subjects: | Artificial Intelligence (cs.AI); Signal Processing (eess.SP) |
| Cite as: | arXiv:2610.32542 [cs.AI] |
| (or arXiv:2610.32542v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32542 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ranjani H. G. [view email]
[v1]
Fri, 23 Oct 2026 12:21:27 UTC (1,274 KB)
来源：arXiv cs.AI · arxiv.org