Semantic IDs derived from Multi-modal Large Language Models (MLLMs) integrate rich content semantics into recommendation systems but often lack the collaborative signals crucial for capturing user behavior. Additionally, static generation fails to adapt to evolving data distributions, causing codebook drift. To address these limitations, we propose a dynamic End-to-End Semantic ID Generation Framework based on Decoupled Representation Alignment. Our method aligns shared and private components from both MLLM content and Collaborative Filtering (CF) embeddings, integrating them via a hierarchical adaptive fusion module into a Residual Quantized Variational Autoencoder (RQ-VAE). This joint optimization promotes both semantic granularity and collaborative awareness while supporting dynamic codebook updates. Extensive offline experiments and online A/B tests on Alipay's Tab3 short-video scenario demonstrate the superiority of our method, which is now deployed to serve all users.

User interest modeling is foundational to recommender systems. However, sparse and noisy behaviors make traditional item-level sequence models brittle, especially for new and low-activity users. Furthermore, relying solely on a user's own history limits exploration and reinforces the ''filter bubbles''. To address this, we propose GEM (Generative Enhanced Modeling). GEM shifts the paradigm from self-behavior induction to collective experience migration. Specifically, it constructs LLM-based semantic IDs and embeddings. Grounded in information theory, GEM performs multi-stage denoising at both the user and item levels. This design effectively suppresses reward-driven noise while preserving target-aware signals. We deployed GEM on the Alipay Tab3 video feed. Offline evaluations show significant GAUC gains. Online A/B tests demonstrate a 0.9% lift in watch time alongside stable video views and improved exposure diversity. These results confirm that GEM enhances recommendation quality and successfully broadens user interests.

Recently, graph neural networks have shown the superiority of modeling the complex topological structures in heterogeneous network-based recommender systems. Due to the diverse interactions among nodes and abundant semantics emerging from diverse types of nodes and edges, there is a bursting research interest in learning expressive node repre-sentations in multiplex heterogeneous networks. One of the most important tasks in recommender systems is to predict the potential connection between two nodes under a specific edge type (i.e., relationship). Although existing studies utilize explicit metapaths to aggregate neighbors, practically they only consider intra-relationship metapaths and thus fail to leverage the potential uplift by inter-relationship information. Moreover, it is not always straightforward to exploit inter-relationship metapaths comprehensively under diverse relationships, espe-cially with the increasing number of node and edge types. In addition, contributions of different relationships between two nodes are difficult to measure. To address the challenges, we propose HybridGNN, an end-to-end GNN model with hybrid aggregation flows and hierarchical attentions to fully utilize the heterogeneity in the multiplex scenarios. Specifically, HybridGNN applies a randomized inter-relationship exploration module to exploit the multiplexity property among different relationships. Then, our model leverages hybrid aggregation flows under intra-relationship metapaths and randomized exploration to learn the rich semantics. To explore the importance of different aggregation flow and take advantage of the multiplexity property, we bring forward a novel hierarchical attention module which leverages both metapath-Ievel attention and relationship-level attention. Extensive experimental results on five real-world datasets suggest that HybridGNN achieves the best performance compared to several state-of-the-art baselines (p < 0.01, t-test) with statistical significance.

In this paper, a novel subject-adaptable heartbeat classification model is presented, in order to address the significant interperson variations in ECG signals. A multiview learning approach is proposed to automate subject adaptation using a small amount of unlabeled personal data, without requiring manual labeling. The designed subject-customized models consist of two models, namely, general classification model and specific classification model. The general model is trained using similar subjects out of a population dataset, where a pattern matching based algorithm is developed to select the subjects that are "similar" to the particular test subject for model training. In contrast, the specific model is trained mainly on a small amount of high-confidence personal dataset, resulting from multiview-based learning. The learned general model represents the population knowledge, providing an interperson perspective for classification, while the specific model corresponds to the specific knowledge of the subject, offering an intraperson perspective for classification. The two models supplement each other and are combined to achieve improved personalized ECG analysis. The proposed methods have been validated on the MIT-BIH Arrhythmia Database, yielding an average classification accuracy of 99.4% for ventricular ectopic beat class and 98.3% for supraventricular ectopic beat class, which corresponds to a significant improvement over other published results.

In order to enable unobtrusive human object interaction detection, we propose a minimalistic approach to instrumenting everyday objects with passive (i.e. battery-free) UHF RFID tags. By measuring the changes in the physical layer of the communication channel between the RFID tag and reader (such as RSSI, RF phase, and read rate) we are able to classify, in real time, tag/object motion events along with two types of touch events. Through a user study, we demonstrate that our real-time classification engine is able to simultaneously track 20 objects and identify four movement classes with 93% accuracy. To demonstrate how robust this general-purpose interaction mechanism is, we investigate three usage scenarios 1) interactive storytelling with toys 2) inference of daily activities in the home 3) identification of customer browsing habits in a retail setting.