Many internet companies operate multiple flagship applications, each of which can be regarded as a distinct business domain, covering areas such as video, reading, and gaming. Within each domain, diverse recommendation scenarios coexist, and users engage in various tasks with heterogeneous behaviors. In our industrial setting, we observe three key phenomena that existing methods rarely address: (i) users' Cross-Domain Interests (CDI) are weakly exploited, since behavior sequences are often pooled for efficiency, losing transferable cross-domain dependencies; (ii) multi-domain, scenario, and task variations are under-modeled, making it difficult to capture fine-grained complementarities; and (iii) multimodal features remain misaligned with ID features, especially when different domains emphasize different modalities. These gaps hinder cross-product collaboration.

This paper presents CoCube a tabletop modular robotics platform designed for robotics education and multirobot algorithm research. CoCube is characterized by its low cost low floors high ceilings and wide walls offering flexibility and broad applicability across various use cases. The platform comprises four key components: CoCube robots which integrate wireless communication movement and interaction; CoModules which provide versatile external functionality; CoMaps which enable high-precision localization via microdot patterns on regular printed paper; and CoTags for interaction. CoCube operates on MicroBlocks a blocks programming language for physical computing inspired by MIT Scratch a widely-used coding language with a simple visual interface that makes programming accessible to young learners. It offers users both flexibility and ease of use with advanced API support for more complex applications. This paper details the design of the CoCube platform and demonstrates its potential in both educational and research contexts.

Many signals in the real world are nonlinear and complex, and signal time-frequency analysis has been widely used in many fields. It remains a challenging task to accurately decompose amplitude modulation-frequency modulation (AM-FM) signals with complex variation laws. The existing methods still have room to improve the decomposition accuracy of complex AM-FM signals, such as signals with crossing instantaneous frequency (IF) or close IFs. This article presents a novel sparsity-assisted variational nonlinear component decomposition (SVNCD) for analyzing nonstationary multicomponent signal with complex variation laws. To better restrict the bandwidth of demodulated signal and accurately estimate IF, SVNCD establishes a new sparse optimization model with clear mathematical meaning for the demodulated signal of the original signal, considering the smoothness and Fourier spectrum constraints. Moreover, SVNCD establishes a sparse constraint optimization model on the IF of the signal and its increment, which is capable of effectively extracting the IF variation law of complex signals and addressing the mode aliasing problem. Besides, we build a unified framework for extracting the initial IFs of complex signals with uncrossing or crossing frequency trajectories. The decomposition experiments of various simulated and experimental complicated signals are carried out for verification. The results verify that SVNCD achieves better decomposition accuracy for complex nonstationary multicomponent signals with uncrossing or crossing frequency trajectories than existing signal decomposition and time-frequency transform methods. Moreover, SVNCD could accurately estimate the IF of the original signal and reconstruct the subsignals.

Extensive research has been conducted on assessing grasp stability, a crucial prerequisite for achieving optimal grasping strategies, including the minimum force grasping policy. However, existing works employ basic feature-level fusion techniques to combine visual and tactile modalities, resulting in the inadequate utilization of complementary information and the inability to model interactions between unimodal features. This work proposes an attention-guided cross-modality fusion architecture to comprehensively integrate visual and tactile features. This model mainly comprises convolutional neural networks (CNNs), self-attention, and cross-attention mechanisms. In addition, most existing methods collect datasets from real-world systems, which is time-consuming and high-cost, and the datasets collected are comparatively limited in size. This work establishes a robotic grasping system through physics simulation to collect a multimodal dataset. To address the sim-to-real transfer gap, we propose a migration strategy encompassing domain randomization and domain adaptation techniques. The experimental results demonstrate that the proposed fusion framework achieves markedly enhanced prediction performance (approximately 10%) compared to other baselines. Moreover, our findings suggest that the trained model can be reliably transferred to real robotic systems, indicating its potential to address real-world challenges.