EUVIMEDEUVIMED entdecken
Crossref

Scaling Law for Large Wireless Models

Ziheng Liu, Jiayi Zhang, Haoyu Wang, Bokai Xu, Chen Zhang, Yiyang Zhu, Enyu Shi

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (28) · 24017-24025

DOI: 10.1609/aaai.v40i28.39579 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Ziheng Liu und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Emerging from recent advances in foundation models, Large Wireless Models (LWMs) represent a new paradigm of general-purpose intelligence for wireless communications that transcends task-specific engineering. The success of foundation models is critically underpinned by scaling laws, which provide a predictable roadmap for how performance scales with resources. However, established scaling laws from language and vision, charting performance as a power-law of model and dataset sizes, are ill-suited for the wireless domain, as their core formulations cannot model the structured nature of the physical channel. To address this, we propose a novel wireless scaling law that extends the classical formulation by modeling two wireless-native factors: channel heterogeneity and discretization granularity. These two factors reshape scaling behavior via nested linear and power-law relationships, recasting the scaling law's parameters (notably the scaling exponent and irreducible loss) from universal constants into dynamic variables dictated by the physical environment. Our physics-aware formulation reveals two key insights: first, that compute-optimal scaling is not dictated by a fixed model-data ratio but is instead a dynamic function of heterogeneity and granularity, and second, that this dependency is particularly sensitive to granularity, allowing significant performance to be unlocked from existing data simply by refining its resolution. Crucially, this establishes a reliable roadmap for designing powerful yet resource-efficient LWMs, translating theoretical insights into actionable engineering principles. Extensive experiments validate our wireless scaling law, showing a 32.31% prediction accuracy improvement over classical laws in diverse wireless scenarios where they fail.

Zitieren

APA

Liu, Z., Zhang, J., Wang, H., Xu, B., Zhang, C., Zhu, Y., & Shi, E. (2026). Scaling Law for Large Wireless Models. Proceedings of the AAAI Conference on Artificial Intelligence, 40(28), 24017-24025. https://doi.org/10.1609/aaai.v40i28.39579

Vancouver

Liu Z, Zhang J, Wang H, Xu B, Zhang C, Zhu Y, et al. Scaling Law for Large Wireless Models. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(28):24017-24025. doi:10.1609/aaai.v40i28.39579

BibTeX
@article{Liu2026,
  author = {Liu, Ziheng and Zhang, Jiayi and Wang, Haoyu and Xu, Bokai and Zhang, Chen and Zhu, Yiyang and Shi, Enyu},
  title = {Scaling Law for Large Wireless Models},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {28},
  pages = {24017--24025},
  doi = {10.1609/aaai.v40i28.39579}
}
Kostenlos starten →