arXiv:2603.22316v1 Announce Type: cross Abstract: Group dance generation from music requires synchronizing multiple dancers while maintaining spatial coordination, making it highly relevant to applications such as film production, gaming, and animation. Recent group dance generation models have achieved promising generation quality, but they remain difficult to deploy in interactive scenarios due to bidirectional attention dependencies. As the number of dancers and the sequence length increase, the attention computation required for aligning music conditions with motion sequences grows quadratically, leading to reduced efficiency and increased risk of motion collisions. Effectively modeling dense spatial-temporal interactions is therefore essential, yet existing methods often struggle to capture such complexity, resulting in limited scalability and unstable multi-dancer coordination. To address these challenges, we propose ST-GDance++, a scalable framework that decouples spatial and temporal dependencies to enable efficient and collision-aware group choreography generation. For spatial modeling, we introduce lightweight distance-aware graph convolutions to capture inter-dancer relationships while reducing computational overhead. For temporal modeling, we design a diffusion noise scheduling strategy together with an efficient temporal-aligned attention mask, enabling stream-based generation for long motion sequences and improving scalability in long-duration scenarios. Experiments on the AIOZ-GDance dataset show that ST-GDance++ achieves competitive generation quality with significantly reduced latency compared to existing methods.

Background: The rapid digitalization of health care has reshaped access to medical services. However, older adults often remain disadvantaged due to the digital divide. Electronic health literacy (EHL) is increasingly recognized as a determinant of health-related quality of life (HRQoL); however, its mechanisms and subgroup differences in China remain underexplored. Objective: This study aimed to examine the association between EHL and multidimensional HRQoL among Chinese older adults, with a focus on the mediating roles of attitudes toward own aging (ATOA) and self-efficacy (SE), and heterogeneity by age, residence, and lifestyle. Methods: A cross-sectional survey (July-November 2024) included 8364 adults aged ≥55 years from 4 provinces using stratified multistage sampling. HRQoL was measured by physical health (PH), mental health (MH), and life satisfaction (LS). EHL was assessed with the eHealth Literacy Scale (eHEALS), ATOA with the Philadelphia Geriatric Center Morale Scale subscale, and SE with the General Self-Efficacy Scale. Analyses used seemingly unrelated regressions, PROCESS (Andrew F. Hayes) macro mediation with 5000 bootstraps, and subgroup regressions. Results: EHL was positively associated with PH (=0.273;