Site-Specific Learning for Wireless Networks via Digital Twins
This research explores the integration of digital twins with machine learning to enable site-specific optimization in wireless networks. By leveraging high-fidelity virtual representations of physical spaces, we develop efficient learning frameworks that significantly improve communication and sensing performance. Unlike conventional machine learning approaches that rely on generalized datasets or statistical channel models for broad applicability, our models exploits the precise spatial and electromagnetic characteristics of a given environment. By prioritizing local accuracy over generic solutions, these digital twin-driven, site-specific models generate highly tailored, robust, and efficient network configurations, bridging the gap between theoretical models and real-world deployment.
- Generative Site-Specific Beamforming for
Next-Generation Spatial Intelligence
Z. Wang, Z. Zhou, C. J. Zhao, and Y. Liu,
arXiv preprint arXiv:2601.02301, 2026 - Beam-Brainstorm: A Generative Site-Specific
Beamforming Approach
Z. Zhou, Z. Wang, and Y. Liu,
arXiv preprint arXiv:2601.02219, 2026 - Generative Site-Specific Beamforming via
Information-Maximizing Codebook
C. J. Zhao, Z. Wang, and Y. Liu,
arXiv preprint arXiv:2602.12552, 2026
