Yang Li

Yang Li, Xing Zhang, Yan Zhang et al.

The 6G network will support six major application scenarios, such as immersive communication, integrated AI and communication, and integrated sensing and communication. Many scenarios necessitate significant computational support. Moreover, user demands are becoming increasingly segmented, diverse, and personalized. Traditional network slicing alone is insufficient to meet the heterogeneous computing and networking demands of emerging service scenarios. Mobile computing network convergence (CNC) introduces a fundamentally different paradigm from the conventional cloud computing plus communication network model by deeply embedding computing resources into the mobile network infrastructure and enabling integrated computing-network services tailored to diverse user demands. In this article, we investigate orchestration architectures and mechanisms for CNC in 6G mobile networks. We begin by reviewing the evolution of CNC from a mobile network perspective and surveying existing studies, which we categorize according to mobile network architectures. Building on these insights, we propose a hierarchical, cross-domain coordination architecture and an orchestration mechanism based on hierarchical multi-agent reinforcement learning. Performance evaluations demonstrate that the proposed architecture and mechanism significantly reduce system energy consumption while enhancing task satisfaction rate. Finally, we discuss open challenges and future research directions.

Hanyang Chen, Hongliang Li, Jiarui Cao et al.

Vision-Language-Action models have recently demonstrated promising capabilities in learning generalist robot policies from large-scale multimodal data. However, most existing VLA systems are trained and evaluated primarily with English instructions, leaving their ability to understand and execute instructions in other languages largely unexplored. While the underlying large language models often possess multilingual capabilities, it remains unclear whether these multilingual capabilities transfer to VLAs during training. In this work, we present the first systematic study of multilingual instruction following in VLA models. We first construct multilingual instructions by extending existing benchmarks with translations of their instructions. Using these instructions, we evaluate several representative VLA models across a range of tasks in simulation settings. Our experiments reveal a significant multilingual gap: models trained primarily on English instructions exhibit substantial performance degradation when evaluated on other languages, even when the underlying language backbone is multilingual. We provide several findings and analyses to understand the multilingual gap. Cross-lingual transfer behavior analysis shows that performance drops correlate with both instruction understanding and action execution. Representation analyses suggest that multilingual instruction-caused representation shifts may contribute to the multilingual gap. Motivated by these findings, we further explore strategies to improve multilingual performance in VLAs. We propose a simple yet effective multilingual fine-tuning approach, Multilingual Principal Component Alignment, which leverages Principal Component Analysis to get the principal component subspace and align projected multilingual representations, effectively reducing the multilingual performance gap.