Recent advances in audio-driven talking-head synthesis have brought lip-sync precision close to human perception, yet emotional fidelity and real-time inference remain open challenges. Existing pipelines typically disentangle lip articulation, facial expression, and head pose in latent space; this rigid factorization ignores the intrinsic coupling between articulation and affect — e.g., downward lip corners when sad—thus limiting expressiveness. We cast speech-conditioned facial motion as a sample from an emotion-conditioned distribution in a motion latent space. Concretely, we (i) learn a motion dictionary of orthogonal bases with an autoencoder via self-supervision, (ii) construct emotion-conditioned sub-spaces within the latent space, and (iii) design a layer-progressive cross-attention fusion module that modulates a flow-matching sampler with both audio and emotion signals. Only ten reverse ODE steps are required to generate a motion-latent trajectory, enabling real-time end-to-end latency. Extensive experiments on MEAD and RAVDESS show that our method outperforms recent GAN- and diffusion-based baselines in emotion accuracy while running at around 75 FPS on a single desktop GPU. The proposed framework delivers the first emotionally expressive Audio2Face system that simultaneously achieves lip-sync accuracy, affective realism, and real-time performance.

Visual document retrieval requires understanding heterogeneous and multi-modal content to satisfy implicit information needs. Recent advances use screenshot-based document encoding with fine-grained late interaction to encode holistic information and capture nuanced alignments, significantly improving retrieval performance. However, retrievers are still trained with coarse global relevance labels, without revealing which regions support the match. As a result, retrievers tend to rely on surface-level cues and struggle to capture implicit semantic connections, hindering their ability to handle non-extractive queries. To improve fine-grained relevance modeling, we propose a Attention-Grounded REtriever Enhancement (AGREE) framework. AGREE leverages cross-modal attention from multimodal large language models (MLLMs) as proxy supervision to guide the retriever in identifying relevant document regions. Specifically, AGREE extracts attention maps from the MLLM that highlight which document regions are attended to based on the query. These attention scores serve as local, region-level relevance signals. During training, AGREE combines local signals with the global document-level relevance label to jointly optimize the retriever. This dual-level supervision enables the model to learn not only whether documents match, but also which content drives relevance. Experiments on the challenging visual document retrieval benchmark, ViDoRe V2, show that AGREE significantly outperforms the global-supervision-only baseline by 12.82% and 5.03% in terms of average nDCG@1 and nDCG@5. Quantitative and qualitative analyses further demonstrate that AGREE promotes deeper alignment between query terms and document regions, moving beyond surface-level matching toward more accurate and interpretable retrieval. Our code is available at: https://github.com/VickiCui/AGREE.

The US faces a nursing shortage, particularly in senior care, highlighting the need for enhanced gerontological nursing education. Human-centered immersive Virtual Reality shows promise in improving nursing training, especially when combined with AI technologies. This study explores the use of Intelligent Immersive Virtual Reality (IIVR) in gerontological nursing through six simulated scenarios. A two-stage validation process assessed the tool. Stage one focused on efficacy, including simulation sickness, system usability, and user experience, with fifteen college students. Stage two evaluated motivation, cognitive workload, and efficacy with forty-five end-users in a senior care facility. The results demonstrated that the developed IIVR tool exceeds “acceptable” levels of efficacy and participants can use the tool without user experience issues. The assessments also suggest that participants are more willing to adopt this tool to enhance their daily gerontological nursing skills. Additionally, the cognitive load of the utilizing developed IIVR tool is less than conventional learning approach.

Integrated Sensing and Communication (ISAC) introduces greater challenges to network transmission in terms of delay, bandwidth, and reliability. Achieving stable and efficient congestion control is a critical issue in emerging ISAC scenarios. However, many traditional congestion control algorithms primarily focus on transmission efficiency but perform poorly in ensuring fairness between different data flows. To address this limitation, this paper proposes a queuing-aware fair congestion control (Q-FCC) solution for ISAC. In particular, Q-FCC incorporates a queue status monitoring module which can provide real-time feedback on the queuing delays at targeted network switches. Additionally, this paper analyzes the traditional BBR algorithm and identifies an inherent flaw: longer RTT flows have a higher bandwidth gain coefficient compared to shorter RTT flows, leading to unfairness. Based on this insight, Q-FCC introduces bandwidth gain factor. Q-FCC uses the queue status monitoring module to categorize data flows into three types and interacts with bursty flow endpoints via ACK packets to assist them in calculating the bandwidth gain factor, which enables the control of the transmission rate. Finally, the algorithm was implemented in the Linux kernel. The results of the semi-physical simulation show that Q-FCC outperforms the traditional BBR and CUBIC algorithms in terms of bandwidth fairness and transmission stability, respectively.

The COVID-19 pandemic has resulted in changes in the working environment which shifted the type of systems thinking skills needed for practitioners. These changes include the utilization of a digitalized work environment . To reliably assess practitioners' systems thinking (ST) skills/abilities in a digitalized environment, such as the case of COVID-19, we propose an evaluation approach based on the hybrid weight determination and extended VIKOR model to assess the systems skills of practitioners concerning 7-dimensions of systems thinking. The proposed methodology consists of three phases: the first phase uses a rough set theory to process the assessment data of candidates' systems thinking skills, the ideal interval references of seven systems thinking skills criteria (7-dimension) of practitioners required by an organization is extracted. The second phase is to build a comprehensive weight solution model based on BWM (best-worst method) and entropy weight method (EWM) and analyze the employer's needs under each systems thinking skills dimension. The third phase is to build a new group utility index based on the weight and digital reference and form an extended Vlsekriterijumska Optimizacija I Kompromisno Resenje (E-VIKOR) model to complete the prioritization of practitioners' systems thinking skillset. A case study containing 108 practitioners is conducted to verify the effectiveness of the proposed decision-making model and carry out sensitivity analysis and methods comparison. The results show that the proposed model provides more reliable and robust results for selecting the most appropriate practitioner for the required digitalized job requirements .

In distributed storage systems, the replication mechanisms are usually used to ensure system reliability and data availability. Random replication is widely used in cloud storage systems to prevent data loss. Copyset Replication (CR) as a replication strategy, makes a nearly optimal trade-off between the number of scattered nodes and the probability of data loss. Compared with random replication, CR greatly reduces the probability of data loss caused by node failure. However, CR's random selection strategy makes it difficult to select the optimal copyset based on data characteristics such as calculation and storage. In response to this problem of CR, the Optimal Copyset Replication (OCR) proposed in this paper can select the optimal copyset according to the specified data characteristics and its corresponding node conditions. Finally, combined with Cyberspace Mimicry Defense (CMD) , we implemented OCR in a distributed object storage system and conducted related experiments. When the calculation type data reaches 300,000, the experimental results prove that compared with CR randomly selecting copyset, OCR reduces the data processing time by nearly 10% through selecting the optimal copyset. By setting relevant parameters, OCR can also ensure that the data distribution of each node is relatively uniform, and avoid data skew.

We introduce and compare two prediction systems on the task of replicating human decisions regarding patient admittance in a typical American emergency department. The data-set used describes the patient trajectories in a 65,000 patient per-year emergency department in the United States. Among the descriptive attributes those of prime importance are the severity of the patient's condition and the time they waited to be admitted from the waiting room to the department proper. A recurrent neural network (RNN) is developed to learn the task of selecting the next patient from the waiting-room/queue to be admitted for treatment which is then compared to a heuristic-based selection algorithm currently used in industry for hospital simulation applications. We demonstrate achievable accuracies of 75.29% and 84.97% using the RNN, depending on the type of the data preprocessing used. These accuracies are only potentially and theoretically achievable, respectively. The former's validity hinges on whether certain "anomalous cases" are outliers or not, the second is achieved with the assumed existence of a method for labeling these same cases as anomalous as part of the RNN's input, which may or may not be achievable, pending further consultation with industry experts. Our conclusions hinge on whether or not such cases are outliers though in either case a more sophisticated data-set is desired. If they are not outliers then a more detailed data-set is likely necessary to apply machine learning, or at least our methods, meaningfully to this prediction problem for use in simulated, or real world, hospitals.