Graph foundation models (GFMs) have emerged as a promising paradigm for learning transferable knowledge across diverse graph-structured data. The inherent heterogeneity in features and graph structures poses significant challenges for building scalable and generalizable GFMs. Existing research has employed mixture-of-experts (MoE) models to handle the challenges, assigning the most suitable expert to each graph. Despite this, the underlying mechanisms of MoE within the context of GFMs remain insufficiently explored. In this work, we conduct an in-depth experimental study on an MoE-based GFM and uncover an intriguing finding: the experts ranked second and third assigned by the router perform better than the top-ranked expert. This insight motivates us to investigate the potential of leveraging knowledge embedded across multiple experts. However, directly ensembling the outputs of multiple experts would incur substantial computational overhead, while applying a standard expert merging strategy risks suboptimal performance. To address these challenges, we introduce two enhanced expert merging strategies that retain the computational efficiency of expert merging, while improving performance to approach the effectiveness of expert ensembling. Specifically, we propose (i) a knowledge distillation-inspired expert merging method that aligns the behavior of parameter-fused experts with expert ensembles, and (ii) a theoretical parameter proximity approach that leverages the similarity of expert parameters to approximate ensemble outputs while preserving diversity. Extensive experiments demonstrate that our methods effectively enhance model performance.

Aiming at the tracking control for an unmanned aerial vehicle (UAV) with uncertainty and external disturbances, an adaptive optimization control method is proposed based on the backstepping method. The model uncertainty in the UAV is estimated using neural networks. Moreover, a disturbance observer is designed to estimate and counteract the disturbance in real-time. In addition, reinforcement learning (RL) is used to solve optimal problems and overcome the difficult issues of the Hamilton-Jacobi-Bellman (HJB) equation. In the controller design, dynamic surfaces are employed to avoid complex derivation issues in the virtual controller and improve operating efficiency. Furthermore, the stability of the UAV system is proved by the Lyapunov theory. Finally, the effectiveness and superiority of the proposed method are verified through numerical simulations and real-world experiments.

Recently, a new form of telexistence is achieved by recording images with cameras on an unmanned aerial vehicle (UAV) and displaying them to the user via a head mounted display (HMD). A key problem here is how to provide a free and natural mechanism for the user to control the viewpoint and watch a scene. To this end, we propose an improved rate-control method with an adaptive origin update (AOU) scheme. Without the aid of any auxiliary equipment, our scheme handles the self-centering problem. In addition, we present a full 6-DOF viewpoint control method to manipulate the motion of a stereo camera, and we build a real prototype to realize this by utilizing a pan-tilt-zoom (PTZ) which not only provides 2-DOF to the camera but also compensates the jittering motion of the UAV to record more stable image streams.

Green communications is put forward to decrease the operational expenditure (OpEx) and carbon emission of communication networks in recent years. The relationship between spectrum efficiency (SE) and energy efficiency (EE) has induced more attentions in academic field, however, most efforts are spent on SE-EE trade-off of link-level not system-level. In this paper, we analyze the trade-off between average area SE (A2SE) and EE under the realistic power consumption model (PCM) in system-level perspective. First, we give the theoretical closed-form expression of A2SE for a cell as a function of edge SNR. And then, closed-form approximation (CFA) of A2SE is derived, and it largely coincides with theoretical A2SE and is reversible. Based on the CFA, we find the closed-form trade-off of A2SEEE concisely. Further, the optimal EE, corresponding A2SE and transmission power of BS under different cell radiuses are got according to the A2SE-EE trade-off. These results are helpful to design cell radius and transmission power which meet different needs for A2SE and EE of wireless networks.