The rapid expansion of latency-sensitive applications has sparked renewed interest in deploying edge computing capabilities aboard satellite constellations, aiming to achieve truly global and seamless service coverage. On one hand, it is essential to allocate the limited onboard computational and communication resources efficiently to serve geographically distributed users. On the other hand, the dynamic nature of satellite orbits necessitates effective service migration strategies to maintain service continuity and quality as the coverage areas of satellites evolve. We formulate this problem as a spatio-temporal Markov decision process, where satellites, ground users, and flight users are modeled as nodes in a time-varying graph. The node features incorporate queuing dynamics to characterize packet loss probabilities. To solve this problem, we propose a Graph-Aware Temporal Encoder (GATE) that jointly models spatial correlations and temporal dynamics. GATE uses a two-layer graph convolutional network to extract inter-satellite and user dependencies and a temporal convolutional network to capture their short-term evolution, producing unified spatio-temporal representations. The resulting spatial-temporal representations are passed into a Hybrid Proximal Policy Optimization (HPPO) framework. This framework features a multi-head actor that outputs both discrete service migration decisions and continuous resource allocation ratios, along with a critic for value estimation. We conduct extensive simulations involving both persistent and intermittent users distributed across real-world population centers. The results validate that the proposed framework consistently achieves superior performance compared to Proximal Policy Optimization (PPO), Soft Actor Critic (SAC), and ablated baselines in terms of reward, failure rate, and migration overhead, demonstrating the effectiveness of the proposed spatio-temporal modeling and hybrid reinforcement learning approach in dynamic satellite edge environments.

Recently, with the users' growing demand for communication rate and capacity in wireless networks, Unmanned Aerial Vehicles (UAVs) have attracted widespread attention due to their mobility, flexibility, and robust line-of-sight communication links. By equipping UAVs with multiple communication payloads, we can construct an aerial wireless network with three-dimensional coverage. However, due to the limitations of UAV onboard energy and communication resources, the lifetime and performance of UAV-assisted wireless networks are significantly constrained. This paper mainly focuses on equipping UAVs with mobile base stations to enhance wireless communication coverage and capacity. We propose a Joint Optimization of 3D Trajectory and Resource Allocation (JOTRA) scheme to maximize energy efficiency in complex scenarios with multi-user mobility and diverse requirements (e.g., UAV-assisted post-disaster search and rescue). Specifically, we apply Dinkelbach's iterative method and Block Coordinate Descent (BCD) method to solve the formulated multivariable and non-convex maximization problem. The algorithm's convergence has been analyzed. According to the simulation, the proposed algorithm can converge faster while maximizing energy efficiency in complex wireless communication scenarios.

Liyan Wang, Haotong Wang, Yves Lepage. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

This paper introduces Continued Pre-training on Analogies (CPoA) to incorporate pre-trained language models with analogical abilities, aiming at improving performance in low-resource translations without data augmentation. We continue training the models on sentence analogies retrieved from a translation corpus. Considering the sparsity of analogy in corpora, especially in low-resource scenarios, we propose exploring approximate analogies between sentences. We attempt to find sentence analogies that might not conform to formal criteria for entire sentences but partial pieces. When training the models, we introduce a weighting scalar pertaining to the quality of analogies to adjust the influence: emphasizing closer analogies while diminishing the impact of far ones. We evaluate our approach on a low-resource translation task: German-Upper Sorbian. The results show that CPoA using 10 times fewer instances can effectively attain gains of +1.4 and +1.3 BLEU points over the original model in two translation directions. This improvement is more pronounced when there are fewer parallel examples.