Involution, characterized by intensified competition for limited social resources without generating additional societal value, has become a critical issue in modern social systems. This study aims to investigate effective mechanisms to mitigate involution by incorporating other-regarding preferences (ORP) into evolutionary game dynamics on complex networks and in well-mixed populations. Through numerical simulations conducted on square lattices and small-world networks, we systematically analyze the combined effects of crucial parameters including total social resources, the cost of more effort, fairness in resource distribution, and the intensity of ORP on the evolutionary dynamics of involution. Our findings reveal that increasing social resources generally exacerbates involution, whereas greater fairness in resource distribution alleviates it. Notably, the influence of more effort costs on involution is nonlinear and context-dependent, modulated by the interaction between resource abundance and ORP intensity. Critically, ORP emerges as a decisive factor: stronger ORP substantially suppresses involution, promotes the emergence and spatial stability of cooperative clusters, and reduces the equilibrium proportion of defectors. Theoretical analysis based on replicator dynamics validate our simulation results, providing robust theoretical benchmarks for the observed phenomena. This study not only advances the theoretical understanding of involution dynamics but also offers practical insights for addressing involution in real-world social systems. It highlights the importance of cultivating altruistic social norms and ensuring fairness in resource allocation to effectively mitigate involution.

Recently, cluster-based methods have achieved significant success in unsupervised re-ID tasks. The hierarchical clustering algorithm, exemplified by SpCL, has been widely adopted in unsupervised cross-domain adaptation and unsupervised learning. The momentum-based feature update mechanism in SpCL has been integrated into various algorithms, achieving notable results in subsequent studies. In this paper, we propose a multi-queue feature updating algorithm that stores feature vectors corresponding to person IDs in multiple queues. Random sampling is then applied to construct the negative sample matrix for contrastive loss, addressing the limitations of momentum-based updating methods. Additionally, we replace the static temperature coefficient in contrastive loss with a trainable temperature coefficient, enabling the model to automatically balance sensitivity between easy and hard samples. The code is available at https://github.com/bmfarer/multi-queue.git.

This paper presents a Long Short-Term Memory network-based Fluid Experiment Data-Driven model (FEDLSTM) for predicting unsteady, nonlinear hydrodynamic forces on the underwater quadruped robot we constructed. Trained on experimental data from leg force and body drag tests conducted in both a recirculating water tank and a towing tank, FED-LSTM outperforms traditional Empirical Formulas (EF) commonly used for flow prediction over flat surfaces. The model demonstrates superior accuracy and adaptability in capturing complex fluid dynamics, particularly in straightline and turning-gait optimizations via the NSGA-II algorithm. FED-LSTM reduces deflection errors during straight-line swimming and improves turn times without increasing the turning radius. Hardware experiments further validate the model's precision and stability over EF. This approach provides a robust framework for enhancing the swimming performance of legged robots, laying the groundwork for future advances in underwater robotic locomotion.

This paper designs a smart grid energy-saving control system for real-time video streaming, named Eco-VisionGrid. According to the real-time video stream collected by the camera, through the location analysis model and intelligent lighting control model deployed on the edge device, it analyzes the location information of the person and forms the best lighting decision. Preliminary experimental results show that Eco-VisionGrid can effectively implement power regulation and management.