This paper proposes ConsisFormer, a compute-efficient Transformer design for wireless foundation models (WFMs) using short-term channel consistency and adaptive token aggregation.

The paper introduces Loopie, two Mixture-of-Experts models that outperform vanilla Transformer baselines in looped Transformers, with extensive ablation studies and a strong reasoning pipeline.

This survey examines explainable AI (XAI) in wireless PHY layers, formalizing goals, taxonomy, and applications.

The paper analyzes the expressivity of padded transformers, proving that their computational power is primarily determined by model depth and numeric precision, rather than attention type or width.

The paper introduces The AI Telco Engineer (AITE), a framework for autonomously designing wireless communication algorithms using large language models, achieving better performance and reduced latenc…

The paper introduces RadioMaster, a novel multi-agent system that successfully translates high-level user intents into physically viable, real-world radio signals, significantly outperforming existing…

The paper introduces Chimera, a highly efficient and scalable MCU designed for ultra-low-power edge AI inference, achieving 3.1 TOPS/W by integrating a dedicated transformer accelerator and a QoS-guar…

This paper proposes a protocol framework for making the 6G air interface AI-native, focusing on interoperability and preserving implementation freedom.

This paper proposes a new communication framework, TokCom, for 6G wireless networks where tokens from large language models become the fundamental entities for information exchange.

This paper isolates the effect of state update design in causal self-attention and introduces structural interventions to reduce approximation errors, outperforming prior post hoc baselines on long-co…

This paper proposes a new architecture for transformer-based language models called 'former', which allocates capacity non-uniformly across network depth by maintaining wider early and late layers whi…

This paper presents a tutorial-and-survey on integrating agentic AI into Next-Generation Networks (NGNs), addressing the gap in protocol integration, evaluation, and standardization alignment.

This paper proposes the Parameter-Efficient Hybrid Transformer (PEHT) framework for network traffic prediction in urban cellular networks, which integrates mobility and congestion information, reduces…