# A Multi-Modal Foundational Model for Wireless Communication and Sensing

arXiv: https://arxiv.org/abs/2602.04016 · HTML: https://mlsanity.com/paper/2602.04016/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 3 Feb 2026.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [Multimodal Masked Autoencoders Learn Transferable Representations](https://mlsanity.com/paper/2205.14204/) (2022)
- [LLM4CP: Adapting Large Language Models for Channel Prediction](https://mlsanity.com/paper/2406.14440/) (2024)
- [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)
- [Reconfigurable Intelligent Surface Assisted Multiuser MISO Systems Exploiting Deep Reinforcement Learning](https://mlsanity.com/paper/2002.10072/) (2020)
- [WiFo: Wireless Foundation Model for Channel Prediction](https://mlsanity.com/paper/2412.08908/) (2024)
- [Generative AI for Integrated Sensing and Communication: Insights from the Physical Layer Perspective](https://mlsanity.com/paper/2310.01036/) (2023)
- [LLM4WM: Adapting LLM for Wireless Multi-Tasking](https://mlsanity.com/paper/2501.12983/) (2025)
- [Large Language Model Based Multi-Objective Optimization for Integrated Sensing and Communications in UAV Networks](https://mlsanity.com/paper/2410.05062/) (2024)
- [Large Language Model Enabled Multi-Task Physical Layer Network](https://mlsanity.com/paper/2412.20772/) (2024)
- [Integrated Sensing and Communication for 6G: Ten Key Machine Learning Roles](https://mlsanity.com/paper/2208.02157/) (2022)
- [Large Wireless Localization Model (LWLM): A Foundation Model for Positioning in 6G Networks](https://mlsanity.com/paper/2505.10134/) (2025)
- [Deep Learning for Direct Hybrid Precoding in Millimeter Wave Massive MIMO Systems](https://mlsanity.com/paper/1905.13212/) (2019)
- [Deep Learning-Aided 6G Wireless Networks: A Comprehensive Survey of Revolutionary PHY Architectures](https://mlsanity.com/paper/2201.03866/) (2022)
- [Localization as a key enabler of 6G wireless systems: A comprehensive survey and an outlook](https://mlsanity.com/paper/2302.02107/) (2023)
- [The Bridge Toward 6G: 5G-Advanced Evolution in 3GPP Release 19](https://mlsanity.com/paper/2312.15174/) (2023)
- [Towards channel foundation models (CFMs): Motivations, methodologies and opportunities](https://mlsanity.com/paper/2507.13637/) (2025)
- [Geo2SigMap: High-Fidelity RF Signal Mapping Using Geographic Databases](https://mlsanity.com/paper/2312.14303/) (2023)
- [Csi-LLM: A Novel Downlink Channel Prediction Method Aligned with LLM Pre-Training](https://mlsanity.com/paper/2409.00005/) (2024)
- [Prompt-Enabled Large AI Models for CSI Feedback](https://mlsanity.com/paper/2501.10629/) (2025)
- [SpectrumFM: A Foundation Model for Intelligent Spectrum Management](https://mlsanity.com/paper/2505.06256/) (2025)
- [Large AI Models for Wireless Physical Layer](https://mlsanity.com/paper/2508.02314/) (2025)

## Built on by (most cited first, 2 of 2)

- [WALoMA: A Multitask Wireless Foundation Model via Adaptive Low-Rank Masked Autoencoders](https://mlsanity.com/paper/2607.25763/) (2026)
- [Wireless Foundation Models: State-of-the-Art and Open Challenges](https://mlsanity.com/paper/2609.04707/) (2026)

## Abstract (arXiv)

Artificial intelligence is a key enabler for next-generation wireless communication and sensing. Yet, today's learning-based wireless techniques do not generalize well: most models are task-specific, environment-dependent, and limited to narrow sensing modalities, requiring costly retraining when deployed in new scenarios. This work introduces a task-agnostic, multi-modal foundational model for physical-layer wireless systems that learns transferable, physics-aware representations across heterogeneous modalities, enabling robust generalization across tasks and environments. Our framework employs a physics-guided self-supervised pretraining strategy incorporating a dedicated physical token to capture cross-modal physical correspondences governed by electromagnetic propagation. The learned representations enable efficient adaptation to diverse downstream tasks, including massive multi-antenna optimization, wireless channel estimation, and device localization, using limited labeled data. Our extensive evaluations demonstrate superior generalization, robustness to deployment shifts, and reduced data requirements compared to task-specific baselines.