MultiPathFormer: Towards a Foundation Model for Multipath Wireless Propagation
Blessed Guda, Kayley Sze, Carlee Joe-Wong
cs.LG, cs.AI, eess.SP
Submitted: 2026-08-05
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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
Terminology
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. 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. In this work, we propose to instead use multipath propagation as the fundamental pretraining object. We present MultiPathFormer, an autoregressive foundation model that represents each transmitter-receiver link as an ordered sequence of continuous-valued path tokens and pretrains with next-path prediction. We introduce an Environmental RAG (retrieval-augmented generation) mechanism and a first-path codebook on top of the transformer backbone, leveraging environment knowledge to improve path statistics estimation like delay and power by up to 59%. MultiPathFormer pretrained on 27 environments transfers to unseen users and, after scenario-specific fine-tuning, outperforms training the corresponding models from scratch in new environments. Across downstream tasks, it outperforms SOTA channel-based foundation models, achieving 5.57 m mean localization error, 0.914 top-3 beam accuracy, 0.994 line-of-sight classification accuracy, and 0.561 channel estimation NMSE. These results show that path-level pretraining can learn reusable representations of wireless propagation.
Sources
- On the Opportunities and Risks of Foundation Models
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Learning Transferable Visual Models From Natural Language Supervision
- A Generalist Agent
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- ChannelGPT: A Large Model to Generate Digital Twin Channel for 6G Environment Intelligence
- Large Wireless Model (LWM): A Foundation Model for Wireless Channels
- Towards channel foundation models (CFMs): Motivations, methodologies and opportunities
- Masked Autoencoders Are Scalable Vision Learners
- SPA-MAE: A Physics-Guided CSI Foundation Model for Wireless Physical Layer
- A Wireless Foundation Model for Multi-Task Prediction
- WiCo-MG: Wireless Channel Foundation Model for Multipath Generation via Synesthesia of Machines
- Auto-CsiNet: Scenario-customized Automatic Neural Network Architecture Generation for Massive MIMO CSI Feedback
- Deep Learning-Based Channel Estimation
- Sionna: An Open-Source Library for Next-Generation Physical Layer Research
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks