Chen-Shan Ren

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

Dual-Timescale Control for SDN-Enabled Collaborative Inference

In dynamic edge networks, multi-node collaborative inference often suffers from amplified tail latency due to background traffic competition and node load variations. While existing work focuses on static computation-side optimization, it lacks online control over dynamic network factors. To bridge this gap, we propose...

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.