# MultiPathFormer: Towards a Foundation Model for Multipath Wireless Propagation

arXiv: https://arxiv.org/abs/2608.05076 · HTML: https://mlsanity.com/paper/2608.05076/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://mlsanity.com/paper/2109.10282/) (2021)
- [Sionna: An Open-Source Library for Next-Generation Physical Layer Research](https://mlsanity.com/paper/2203.11854/) (2022)
- [DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications](https://mlsanity.com/paper/1902.06435/) (2019)
- [Deep Learning-Based Channel Estimation](https://mlsanity.com/paper/1810.05893/) (2018)
- [Deep Learning for mmWave Beam and Blockage Prediction Using Sub-6GHz Channels](https://mlsanity.com/paper/1910.02900/) (2019)
- [Large Wireless Model (LWM): A Foundation Model for Wireless Channels](https://mlsanity.com/paper/2411.08872/) (2024)
- [WirelessGPT: A Generative Pre-trained Multi-task Learning Framework for Wireless Communication](https://mlsanity.com/paper/2502.06877/) (2025)
- [WiFo: Wireless Foundation Model for Channel Prediction](https://mlsanity.com/paper/2412.08908/) (2024)
- [A Wireless Foundation Model for Multi-Task Prediction](https://mlsanity.com/paper/2507.05938/) (2025)
- [Towards a Wireless Physical-Layer Foundation Model: Challenges and Strategies](https://mlsanity.com/paper/2403.12065/) (2024)
- [ChannelGPT: A Large Model to Generate Digital Twin Channel for 6G Environment Intelligence](https://mlsanity.com/paper/2410.13379/) (2024)
- [Towards channel foundation models (CFMs): Motivations, methodologies and opportunities](https://mlsanity.com/paper/2507.13637/) (2025)
- [Large AI Models for Wireless Physical Layer](https://mlsanity.com/paper/2508.02314/) (2025)
- [Multi-Modal Data-Enhanced Foundation Models for Prediction and Control in Wireless Networks: A Survey](https://mlsanity.com/paper/2601.03181/) (2026)
- [Wireless AI Evolution: From Statistical Learners to Electromagnetic-Guided Foundation Models](https://mlsanity.com/paper/2507.00366/) (2025)
- [WiCo-MG: Wireless Channel Foundation Model for Multipath Generation via Synesthesia of Machines](https://mlsanity.com/paper/2511.15026/) (2025)
- [Auto-CsiNet: Scenario-customized Automatic Neural Network Architecture Generation for Massive MIMO CSI Feedback](https://mlsanity.com/paper/2311.15950/) (2023)

## Abstract (arXiv)

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.