Transformer-based models have achieved dominance in point cloud analysis, yet their quadratic computational complexity remains a fundamental limitation for practical applications. Recently, RWKV has emerged as a promising alternative for sequence modeling due to its linear computational complexity. However, it has yet to be effectively adapted to handle the unordered and sparse nature of point cloud data. In this paper, we propose RWKV3D, an innovative and computational framework tailored for point cloud analysis, which is adaptable to three training strategies: training from scratch, single-modal pre-training, and cross-modal pre-training. First, we replace the MLP layer with an advanced Local Feature Mixer (LFM), which not only enhances fine-grained feature extraction but also reduces the number of parameters. Second, we introduce a Bidirectional Multi-head Shift (BMS) mechanism to expand the receptive field, effectively capturing richer contextual information. Additionally, to enhance high-level feature processing, we strategically incorporate a Multi-head Self-Attention (MSA) block before the first RWKV3D block. Experimental results demonstrate that RWKV3D outperforms Transformer-based and Mamba-based methods while maintaining lower parameter counts and computational costs. Notably, it achieves several state-of-the-art results, including overall accuracies of 95.3% (training from scratch) and 95.9% (cross-modal pre-training) on the ModelNet40 dataset, as well as 95.28% (single-modal pre-training) on the ScanObjectNN (PB_T50_RS) dataset. These results underscore the superior efficacy of the RWKV architecture in 3D vision tasks and highlight its potential for broader multimodal learning scenarios.

As the number of cores in a multicore system increases, the communication pressure on the interconnection network also increases. The network-on-chip (NoC) architecture is expected to take on the ever-expanding communication demands triggered by the ever-increasing number of cores. The communication behavior of the NoC architecture exhibits significant spatial-temporal variation, posing a considerable challenge for NoC reconfiguration. In this paper, we propose a traffic-oriented reconfigurable NoC with augmented inter-port buffer sharing to adapt to the varying traffic flows with a high flexibility. First, a modified input port is introduced to support buffer sharing between adjacent ports. Specifically, the modified input port can be dynamically reconfigured to react to on-demand traffic. Second, it is ascertained that a centralized output-oriented buffer management works well with the reconfigurable input ports. Finally, this reconfiguration method can be implemented with a low overhead hardware design without imposing a great burden on the system implementation. The experimental results show that compared to other proposals, the proposed NoC architecture can greatly reduce the packet latency and improve the saturation throughput, without incurring significant area and power overhead.

Reinforcement learning (RL) has been widely employed in communications, in the areas of interference management, resource allocation, signal detection, and power control, etc. Nevertheless, RL is vulnerable under various malicious attacks, such as adversarial examples and privacy intrusions. In this paper, a falsification attack on the agent actions in a scalar linear quadratic regulator (LQR) system is studied. This adversarial problem is formulated as a novel dynamic game by introducing an adversarial belief, and subgame perfect equilibria (SPEs) are characterized under different adversarial constraints. Numerical experiments show the impact of strategic interactions and justify the theoretic results.

Nowadays, electric traction is applied in highspeed trains, and the effects of crosswind increase the instability of the pantograph turbulence, so higher requirements are put forward for the good contact between pantograph and catenary. A new type of pantograph of working height of 2800 mm and a running speed of 400 km/h was taken as the object in this study. Based on the three-dimensional, steady, incompressible N-S equation and k- ω SST (Shear Stress Transport) turbulence model, the variation of aerodynamic force and aerodynamic lift force with different crosswind speed and yaw angle were analyzed. The results show as follows: aerodynamic force and aerodynamic lift force of pantograph increase with increasing crosswind speed. The most dangerous situation of pantograph occurs while the crosswind speed is 30 m/s and the yaw angle is 60°, where the aerodynamic lift force is twice than without crosswind, and the flow field around the pantograph becomes more complicated, resulting in poor current collection between pantograph and catenary. Consequently, high-speed trains should slow down or stop running in the strong crosswind environment.

iQIYI represents one of the largest scale and most sophisticated video recommendation systems in China. In this paper, we focus on the model architecture as well as feature interpretation of our short video recommendation system. We firstly describe the short video recommendation system of iQIYI at a high level, which follows a three-stage information retrieval dichotomy. A Recommendation System Boosted Local Interpretable Model-Agnostic Explanations (RSLIME) is then proposed for real-time feature interpretation and importance evaluation. Lastly, comprehensive online and offline experiments are conducted to demonstrate the effectiveness of RSLIME and prove its unique advantages in the task of feature importance analysis and feature selection on large scale industrial recommendation systems.

Graphical User Interface (GUI) is a component of many software applications. Many mobile game applications in particular have to provide excellent user experiences using graphical engines to render GUI screens. On a rendered GUI screen such as a treasury map, no GUI widget is embodied in it and the operable GUI regions, each of which is a region that triggers actions when certain events acting on these regions, may only be implicitly determinable. Traditional testing tools like monkey test do not effectively generate effective event sequences over such operable GUI regions. Our insight is that operable regions in a rendered GUI screen of many mobile game applications are given with visible hints to catch user attentions. In this paper, we propose Smart Monkey, which uses the fundamental features of a screen, including color, intensity, and texture, as visual signals to detect operable GUI region candidates, and iteratively identifies and confirms the real operable GUI regions by launching GUI events to the region. We have implemented Smart Monkey as a testing tool for Android apps and conducted case studies on real-world applications to compare it with a peer technique. The empirical results show that it effective in identifying such operable regions and thus able to generate functional event sequences more efficiently.