pith. sign in

arxiv: 2506.24009 · v1 · pith:AZSCQIWXnew · submitted 2025-06-30 · 💻 cs.IT · cs.AI· math.IT

Bridging Physical and Digital Worlds: Embodied Large AI for Future Wireless Systems

Xinquan Wang , Fenghao Zhu , Zhaohui Yang , Chongwen Huang , Xiaoming Chen , Zhaoyang Zhang , Sami Muhaidat , M\'erouane Debbah This is my paper
classification 💻 cs.IT cs.AImath.IT
keywords wirelesslargemodelssystemswelaiactiveembodiedfuture
0
0 comments X
read the original abstract

Large artificial intelligence (AI) models offer revolutionary potential for future wireless systems, promising unprecedented capabilities in network optimization and performance. However, current paradigms largely overlook crucial physical interactions. This oversight means they primarily rely on offline datasets, leading to difficulties in handling real-time wireless dynamics and non-stationary environments. Furthermore, these models often lack the capability for active environmental probing. This paper proposes a fundamental paradigm shift towards wireless embodied large AI (WELAI), moving from passive observation to active embodiment. We first identify key challenges faced by existing models, then we explore the design principles and system structure of WELAI. Besides, we outline prospective applications in next-generation wireless. Finally, through an illustrative case study, we demonstrate the effectiveness of WELAI and point out promising research directions for realizing adaptive, robust, and autonomous wireless systems.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. World Model-Enabled Causal Digital Twins for Semantic Communications in Physical AI Systems

    cs.LG 2026-05 unverdicted novelty 7.0

    Introduces WM-CDT framework with causal information value metric to maximize long-term return-per-bit in semantic communications for physical AI with closed-loop sensing-inference-control.

  2. RadioMaster: Multi-Agent System for Autonomous Radio Signal Generation

    cs.MA 2026-06 unverdicted novelty 6.0

    RadioMaster is a multi-agent system that autonomously generates radio signals from user input using domain knowledge retrieval, collaborative I/Q sample creation, and closed-loop verification, outperforming baselines ...

  3. Robust Hybrid Beamforming with Liquid Crystal Antennas and Liquid Neural Networks

    cs.IT 2026-04 unverdicted novelty 6.0

    A hybrid beamforming framework combining liquid crystal antennas and liquid neural networks delivers 88.6% spectral efficiency gain and improved robustness in 108 GHz urban ray-tracing simulations compared to baseline...

  4. Empowering Embodied AI in 6G Networks: Architecture, Enablers, and Open Challenges

    cs.NI 2026-05 unverdicted novelty 4.0

    Proposes a system-level perception-communication-action architecture for embodied AI-native 6G and identifies enabling technologies plus open challenges.