Multimodal Large Language Models (MLLMs) with Federated Learning (FL) can quickly adapt to privacy-sensitive tasks, but face significant challenges such as high communication costs and increased attack risks, due to their reliance on multi-round communication. To address this, One-shot FL (OFL) has emerged, aiming to complete adaptation in a single client-server communication. However, existing adaptive ensemble OFL methods still need more than one round of communication, because correcting heterogeneity-induced local bias relies on aggregated global supervision, meaning they still do not achieve true one-shot communication. In this work, we make the first attempt to achieve true one-shot communication for MLLMs under OFL, by investigating whether implicit (i.e., initial rather than aggregated) global supervision alone can effectively correct local training bias. Our key finding from the empirical study is that imposing directional supervision on local training substantially mitigates client conflicts and local bias. Building on this insight, we propose YOCO, in which directional supervision with sign-regularized LoRA B enforces global consistency, while sparsely regularized LoRA A preserves client-specific adaptability. Experiments demonstrate that YOCO cuts communication to $\sim$0.03\% of multi-round FL while surpassing those methods in several multimodal scenarios and consistently outperforming all one-shot competitors.

Cloud radio access network (C-RAN) centralizes several baseband units to form a pool, which is the primary form of the wireless network virtualization. Some aspects of C-RAN are always developing, such as the processing capacity and multiple radio access technology (multi-RAT) convergence. In this paper, the Not Only Stack (NO Stack) framework, as a virtualization approach, is suggested to be employed in 5G radio access network (RAN). NO Stack is programmable, flexible, and sustainable, while adopting the mature virtualization technology to achieve a fully virtualized RAN (vRAN). With RAN slicing and network orchestration schemes, the baseband processing and storage resources could be sliced and orchestrated to realize the multi-RAT convergence and flexible reconfiguration. By reconstructing the dedicated and default bearer establishment procedure in long term evolution (LTE), NO Stack framework reduces the signaling and delaying respectively. Seen from the analysis and demonstration, the vRAN based on NO Stack can support multi-RAT convergence and flexible networking, as well as reduce the signaling and delay.