Xinchen Lyu

Consensus-optimized decentralized fine-tuning of foundation models for 6G agentic AI networks

Convergence Analysis of Sequential Federated Learning on Heterogeneous Data

Experimental results validate the counterintuitive analysis result that SFL outperforms PFL on extremely heterogeneous data in cross-device settings and establish the convergence guarantees of SFL for strongly/general/non-convex objectives on heterogeneous data.

Adaptive 3D-RoPE: Physics-Aligned Rotary Positional Encoding for Wireless Foundation Models

Adaptive 3D-RoPE is proposed, a channel-driven 3D rotary positional embedding framework for WFMs to dynamically align the 3D positional embeddings with the instantaneous coherence state of heterogeneous CSI.