Cross-lingual meetings have become essential for global collaboration, yet current translation technologies often strip away vocal identity — the unique speaker characteristics that convey nuance and social presence. While generic text-to-speech (TTS) provides basic intelligibility, it creates a disconnect between speakers and their translated voices, potentially undermining engagement and comprehension. This paper investigates whether voice cloning technology can bridge this gap by preserving speaker identity in real-time translation. We present a controlled study comparing four voice conditions in meeting interpretation: original speech, gender-neutral TTS, gender-matched TTS, and voice cloning. Through a within-subjects experiment with 45 participants, we demonstrate that voice cloning significantly reduces mental workload (p <.001) and enhances user experience across pragmatic quality (p <.001), hedonic quality (p <.001), and overall satisfaction (p <.001) compared to traditional TTS. While original speech maintained advantages in naturalness, voice cloning achieved superior intelligibility, social impression, and user preference. Qualitative analysis revealed that participants valued voice cloning for preserving speaker identity and improving conversation tracking in multi-speaker scenarios. Our findings suggest that identity-preserving translation represents a significant advancement for cross-lingual communication systems, offering both cognitive and social benefits. We conclude with design implications for integrating voice cloning into meeting platforms while addressing ethical considerations around consent and transparency.

Teachers' trust in artificial intelligence (AI) in education depends on how they balance its perceived benefits and risks. Yet global discussions about scaling AI in education rely on fragmented evidence, as most studies of teachers' perceptions focus on single countries or small samples. This lack of representative cross-national evidence limits both theory building and policy development. At the same time, large language models (LLMs) are increasingly used in research, policy, and teachers' professional workflows, despite limited validation in education. To address these gaps, we conduct a large-scale audit of LLM alignment with teachers' perceptions of AI by combining representative international survey data with systematic model evaluation. Using OECD TALIS data from 55 countries and territories, we measure cross-national variation in teachers' perceived benefits and risks of AI. We then benchmark responses from eight state-of-the-art LLMs across four providers under both general and country-specific prompting, comparing higher- and lower-reasoning models. Results reveal substantial cross-national variation in teacher perceptions that is not reliably reflected in LLM outputs. Models compress country differences, overestimate both benefits and risks, and show limited gains from identity prompting or enhanced reasoning. This misalignment matters because LLM-generated guidance and professional discourse increasingly shape how teachers learn about and discuss AI, potentially influencing trust and future adoption decisions. Our findings caution against treating LLM outputs as substitutes for direct engagement with teachers when informing global AI-in-education initiatives. At the same time, some models (e.g., Gemini 3 Fast) partially capture cross-national ranking patterns, suggesting a complementary role in hypothesis generation and exploratory comparative analysis.

Eye-tracking offers new ways to augment our interaction possibilities in extended reality. This paper investigates how gaze can assist pen users in translating shape points within graphical models. By leveraging gaze, we can support the usual design activities with an option where objects can be selected and repositioned through eye movements, with the pen serving as a confirmation tool. This can reduce manual effort and enhance efficiency and ergonomics. To evaluate its effectiveness, we compare four interaction techniques: two pen-based baselines (direct and ray-based) and two gaze-supported methods (gaze for selection and/or object dragging), using a probability based selection scheme. In a user study, 16 participants carried out a shape point translation task and their performance, effort, and user experience were measured. The results highlight the performance trade-offs of each technique—while the gaze-based dragging method introduced marginally more errors, it significantly reduced task time. Our findings offer comparative insights into the strength and limitations of gaze-and pen-based interaction methods, supporting the design of future multimodal 3D design tools.

Collaboration has been shown to enhance creativity, leading to more innovative and effective outcomes. While previous research has explored the abilities of Large Language Models (LLMs) to serve as co-creative partners in tasks like writing poetry or creating narratives, the collaborative potential of LLMs in humor-rich and culturally nuanced domains remains an open question. To address this gap, we conducted a user study to explore the potential of LLMs in co-creating memes---a humor-driven and culturally specific form of creative expression. We conducted a user study with three groups of 50 participants each: a human-only group creating memes without AI assistance, a human-AI collaboration group interacting with a state-of-the-art LLM model, and an AI-only group where the LLM autonomously generated memes. We assessed the quality of the generated memes through crowdsourcing, with each meme rated on creativity, humor, and shareability. Our results showed that LLM assistance increased the number of ideas generated and reduced the effort participants felt. However, it did not improve the quality of the memes when humans were collaborated with LLM. Interestingly, memes created entirely by AI performed better than both human-only and human-AI collaborative memes in all areas on average. However, when looking at the top-performing memes, human-created ones were better in humor, while human-AI collaborations stood out in creativity and shareability. These findings highlight the complexities of human-AI collaboration in creative tasks. While AI can boost productivity and create content that appeals to a broad audience, human creativity remains crucial for content that connects on a deeper level.

Raman spectroscopy offers invaluable insights into the chemical composition and structural characteristics of various materials, making it a powerful tool for structural analysis. However, accurate quantum mechanical simulations of Raman spectra for large systems, such as biological materials, have been limited due to immense computational costs and technical challenges. In this study, we developed efficient algorithms and optimized implementations on heterogeneous computing architectures to enable fast and highly scalable ab initio simulations of Raman spectra for large-scale biological systems with up to 100 million atoms. Our simulations have achieved nearly linear strong and weak scaling on two cutting-edge high-performance computing systems, with peak FP64 performances reaching 400 PFLOPS on 96,000 nodes of new Sunway supercomputer and 85 PFLOPS on 6,000 node of ORISE supercomputer. These advances provide promising prospects for extending quantum mechanical simulations to biological systems.

Quantum perturbation theory is pivotal in determining the critical physical properties of materials. The first-principles computations of these properties have yielded profound and quantitative insights in diverse domains of chemistry and physics. In this work, we propose a portable and scalable OpenCL implementation for quantum perturbation theory, which can be generalized across various high-performance computing (HPC) systems. Optimal portability is realized through the utilization of a cross-platform unified interface and a collection of performance-portable heterogeneous optimizations. Exceptional scalability is attained by addressing major constraints on memory and communication, employing a locality-enhancing task mapping strategy and a packed hierarchical collective communication scheme. Experiments on two advanced supercomputers demonstrate that our implementation exhibits remarkably performance on various material systems, scaling the system to 200,000 atoms with all-electron precision. This research enables all-electron quantum perturbation simulations on substantially larger molecular scales, with a potentially significant impact on progress in material sciences.

To cope with the exponential growth of demand, ultra dense networks (UDNs) are a promising technology in future mobile networks. With small cells densely deployed in networks, how to allocate wireless resources in UDNs efficiently becomes a challenging research topic. In this paper, we concentrate on the distributed user-centric clustering and base station (BS) mode choose problem in UDNs. We formulate a combinatorial optimization problem, with the throughput maximization and power consumption minimization jointly considered in the optimization object. In order to reduce the complexity of the problem, we decompose the original problem into two subproblems in terms of user-centric clustering and BS mode choose, and then solve those subproblems by the max-sum algorithm in sequence. The proposed algorithm can be conducted in a distributed way, and the computational complexity grows linearly with the network size. Simulation results show that the performance of proposed algorithm approaches the performance of the exhaustive algorithm well, and outperforms the conventional algorithm significantly.

With the increasing demands for large-scale computing in Internet of Things network, fog computing emerges as a potential solution. However, the time and energy costs are the bottlenecks for developing fog computing. In this paper, we investigate the green fog computing by maximizing the network utility function considering energy efficiency with the constraints of power and interference. The proposed problem is a large-scale mixed integer nonlinear programming. To deal with such kind of problems, we design an algorithm framework to solve the problem in a distributed and parallel manner. The outer loop of the problem is based on the Benders decomposition to divide the integer variables and continuous variables into the master problems and subproblems, respectively. In the subproblem, we use the Dinkelbach algorithm to transform the fractional programming into an equivalent solvable form. In the inner loop, the large-scale problem with only continuous variables is handled by the alternating direction method of multipliers algorithm. For the master problem, we propose a centralized branch-and-bound algorithm to deal with the complexity. We also discuss the properties and performances of our algorithm. Finally, the simulation results indicate that our proposed algorithm is energy-efficient and time-saving.

To satisfy the rapidly growing demands of wireless communications, new structures have been proposed for the fifth-generation (5G) mobile communication networks, such as cloud radio access networks (C-RANs), which have advantages including high energy efficiency, large network capacity, and high flexibility. This paper concentrates on the problem of remote radio head (RRH) activation, user association, and power allocation in C-RANs. To tackle the problem with l0norm, we transform it into a mixed-integer nonlinear programming (MINLP) problem. Instead of solving it by centralized solvers, we propose a novel algorithm based on Benders decomposition, which can obtain the optimal solution of the MINLP problem. To solve the primal problem in Benders decomposition efficiently, we adopt the alternating direction method of multipliers (ADMM) to achieve a parallel implementation. To further reduce the complexity of solving the MINLP problem, a distributed two-stage iterative algorithm combining the ADMM and the max-sum algorithm is also proposed. The simulation results demonstrate that the first proposed algorithm can obtain the optimal solution, and the second proposed algorithm outperforms conventional algorithms significantly.