The paper introduces a method to enrich Radio Foundation Models (RFMs) by incorporating channel configuration (CFG) information during pre‑training. These CFG‑enriched embeddings are shown to act as effective inductive priors for downstream tasks, especially when labeled data are scarce. Experiments across three data regimes and multiple tasks—LoS/NLoS classification, timing advance estimation, and beam selection—demonstrate that the new embeddings consistently outperform or match baseline models in both in‑distribution and out‑of‑distribution configuration settings.
By Shrihari Vasudevan, H. G. Ranjani, Raaghul Ranganathan, Satwik Sahu, Thirumaran Ekambaram
arXiv:2606. 06373v1 Announce Type: cross Abstract: Wireless foundation models have emerged as a promising alternative to building separate models for each wireless task.
By Ahmed Mohamed, Ahmed Aboulfotouh, Hatem Abou-Zeid
Recent advances in machine learning have enabled training of wireless foundation models, which aim to support tasks such as channel estimation, beam prediction, and localization based on wireless signals. Existing wireless foundation models typically pretrain on channel tensors using masked reconstruction over subcarriers, antennas, or time but ignore the physical characteristics of wireless propagation.
arXiv:2608. 05076v1 Announce Type: cross Abstract: Recent advances in machine learning have enabled training of wireless foundation models, which aim to support tasks such as channel estimation, beam prediction, and localization based on wireless signals.
By Blessed Guda, Kayley Sze, Carlee Joe-Wong
arXiv:2608. 14591v1 Announce Type: cross Abstract: The integration of artificial intelligence (AI) and wireless communications is widely regarded as a core objective of sixth-generation (6G) systems.
By Shugong Xu, Jun Jiang, Yuan Gao
The paper surveys wireless foundation models (WFMs), highlighting their role in learning reusable representations from large-scale wireless data for physical-layer tasks. It systematically reviews WFM design components—pretraining, backbone architectures, and downstream adaptation—and categorizes the literature into five task families: signal recognition and demodulation, channel representation learning, RF sensing and localization, beam management, and spectrum sensing and monitoring, including multi-task models. The analysis reveals that while WFMs show promise, evidence of transferability varies across tasks and evaluation settings, and differences in datasets, modalities, architectures, and distribution shifts hinder clear conclusions about effective design choices.
By Alonso M. Pacheco Huachaca, Juan J. Rodriguez Rodriguez, Ahmed Aboulfotouh, Nelson L. S. da Fonseca, Carlos A. Astudillo, Hatem Abou-Zeid
arXiv:2607. 14975v1 Announce Type: new Abstract: Channel foundation models (CFMs) are developing rapidly, with recent studies reporting benefits from pretraining across downstream wireless tasks.
By Yuan Gao, Wenjun Yu, Jun Jiang, Yunfan Li, Xinyu Guo, Shugong Xu
arXiv:2609.00615v1 Announce Type: cross
Abstract: The evolution toward sixth-generation (6G) wireless networks is driving larger antenna arrays and highly directional multi-beam transmission, making...
By Yue Zhang, Xiucheng Wang, Wenshuo Chen, Nan Cheng
arXiv:2607. 16877v1 Announce Type: cross Abstract: The increasing complexity of next-generation wireless networks has driven the integration of artificial intelligence (AI) into wireless communications.
By Yangjing Wang, Ouya Wang, Shenglong Zhou, Geoffrey Ye Li
The paper introduces RadioDecomp, a method for radiomap blind prediction that corrects a prior‑guided predictor using deterministic residual refinement. It identifies the conditional‑mean radiomap as the optimal target under squared loss and decomposes domain risk into approximation error and irreducible uncertainty. Experiments show that the RadioLSR variant excels in cross‑configuration generalization and outperforms a monolithic baseline in cross‑environment scenarios.
By Xiaojie Li, Yu Han, Han Fang, Shangqing Liu, Shi Jin, Chao-Kai Wen
ChorusTIC is a training‑free foundation model for multivariate time‑series classification that works across heterogeneous channel configurations without updating task‑specific parameters. It uses Random Subchannel Slot Concatenation and a shared dual‑axis encoder to capture temporal and cross‑channel interactions, mapping variable channel counts into a fixed‑width representation. The model is pretrained on synthetic episodes and achieves strong performance on the UEA‑30 and UCR‑128 archives, handling both full‑context and low‑label scenarios without fitting a target‑specific classifier.
By Juntao Fang, Shifeng Xie, Ruichu Cai, Shengji Zheng, Zijian Li, Keli Zhang, Lujia Pan, Themis Palpanas, Zhifeng Hao
arXiv:2607. 11970v1 Announce Type: cross Abstract: We develop an enhanced in-context learning (ICL) framework to improve the performance of pilot-based beamforming in multi-user multiple-input single-output (MU-MISO) systems.
By Yubo Zhang, Xiaodong Wang