Quantum-inspired Machine Learning (QiML) is a burgeoning field, receiving global attention from researchers for its potential to leverage principles of quantum mechanics within classical computational frameworks. However, current review literature often presents a superficial exploration of QiML, focusing instead on the broader Quantum Machine Learning (QML) field. In response to this gap, this survey provides an integrated and comprehensive examination of QiML, exploring QiML's diverse research domains including tensor network simulations, dequantized algorithms, and others, showcasing recent advancements, practical applications, and illuminating potential future research avenues. Further, a concrete definition of QiML is established by analyzing various prior interpretations of the term and their inherent ambiguities. As QiML continues to evolve, we anticipate a wealth of future developments drawing from quantum mechanics, quantum computing, and classical machine learning, enriching the field further. This survey serves as a guide for researchers and practitioners alike, providing a holistic understanding of QiML's current landscape and future directions.
Fine-grained facial expression transfer from humans to humanoid agents presents a unique pattern recognition challenge due to the significant domain gap between biological facial dynamics and mechanical control spaces. While visual synthesis of talking heads has advanced rapidly, mapping high-dimensional visual cues to precise, physically constrained actuation signals remains an open problem, primarily due to the lack of large-scale paired data. To bridge this gap, we introduce X2C, a comprehensive benchmark dataset comprising 100,000 (image, control value) pairs. Unlike existing resources, X2C features nuanced, physically grounded expressions annotated with 30 continuous control parameters, establishing a high-fidelity standard for this task. Building on this resource, we propose X2CNet, a two-stage deep learning framework that explicitly decouples visual motion features from mechanical control regression to model the correspondence between human perceptual cues and humanoid actuation. Extensive experiments, including quantitative benchmarking and real-world physical validation, demonstrate that our approach achieves superior cross-domain consistency and enables robust, in-the-wild expression imitation. Video demonstrations are available at: https://lipzh5.github.io/X2CNet/.
Colloidal quantum dot (CQD) solar cells hold great promise for applications in single-junction and tandem solar cells owing to their adaptable bandgaps. However, power conversion efficiencies (PCEs) of their tandem solar cells still lag far behind their single-junction counterparts, primarily due to suboptimal thicknesses of light harvesting layers and underexplored interlayers for efficient charge recombination. In this study, Silvaco TCAD simulation is first conducted to optimize absorbing layer thickness in the front and rear sub-cells, enabling ideal photocurrent matching. Then, indium tin oxide (ITO) is introduced as an interlayer in a PbS CQD tandem solar cell to achieve efficient charge recombination. Guided by these simulation results, a two-terminal solution-processed PbS CQD tandem solar cell with an ITO interlayer is experimentally fabricated and characterized, which therefore achieved a PCE of 7.4% whereas the control device without an ITO interlayer only delivered a PCE of less than 1%. Therefore, this work offers insights into thickness optimizations of active layers and interlayer engineering for high-performance tandem solar cells, providing a theoretical and experimental guideline for optimizing CQD tandem devices.
Autonomous ground vehicles (AGVs) operating in mountainous and off-road environments need to perform complex local navigation while simultaneously handling severe terrain undulation, intricate obstacle distributions, and task-driven observation requirements. Traditional navigation architectures often rely on decoupled planning and control modules, which makes it difficult to rigorously coordinate nominal guidance with terrain related safety and kinematic constraints. To address these challenges, this paper proposes a unified terrain-aware local navigation framework based on dynamical system modulation and control barrier functions (DSM-CBF), where traversal safety, operational agility, and observation quality are jointly considered. A DSM-based nominal guider is developed to generate continuous and smooth motion commands with natural obstacle avoidance behavior by reshaping the local vector field through anisotropic modulation. The resulting nominal control is then refined by a CBF-based safety filter formulated as a slack-variable-augmented hard quadratic program, so that forward invariance of the safety set can be guaranteed under obstacle clearance, terrain traversability, and speed constraints. Task-related observation metrics, including bistatic geometry as well as range and azimuth resolutions, are further incorporated into the optimization objective to preserve favorable sensing quality during bounded-speed terrain-following motion. Comprehensive simulations and real-vehicle experiments verify the effectiveness and practical executability of the proposed framework. The simulation results show that it satisfies the radial-resolution requirement with an achieved value of approximately 1.01 m relative to the 1.13 m design threshold and improves mission efficiency by about 27% under the observation-quality-prioritized setting; compared with the SOTA methods, the proposed method achieves zero terminal error, maintains an admissible obstacle-clearance margin with min Gamma obs = 1.0439, reduces the turn-RMS by 86.1% and 83.6% relative to A* and D* Lite, respectively, and reduces the computational runtime by 97.9% compared with MPC-CBF, while real-vehicle tests further demonstrate safe and smooth traversal on a physical rugged-terrain AGV platform.
AI chatbots are increasingly being embedded in omnichannel retail ecosystems; however, research on how chatbot service quality relates to customer behavior is limited. In this paper, we conceptualize chatbot service quality (ChatbotSQ) as a formative construct comprising six dimensions: functional, integration, interface, safety, emotional, and personalization quality. Drawing on means-end chain theory, we examine decision confidence as a mechanism underlying the association between chatbot service quality and customers' share of time with the chatbot and omnichannel ecosystem lock-in and explore the moderating role of chatbot comfort level. We use partial least squares structural equation modeling, importance-performance map analysis, and necessary condition analysis to analyze survey data from the United States (N = 345) and Saudi Arabia (N = 302). The results show that chatbot service quality is positively associated with customers' share of time with the chatbot and omnichannel ecosystem lock-in in both countries. These relationships are mediated by decision confidence, which also emerged as a necessary condition for achieving both behavioral outcomes. Chatbot comfort level significantly moderates the relationship between ChatbotSQ and decision confidence in Saudi Arabia but not in the United States, indicating that this boundary condition is context-sensitive across the two samples examined. We also validate a condensed six-item ChatbotSQ measure that provides a parsimonious alternative for research and practice. These findings advance retailing research by showing that AI chatbot service quality is associated with behavioral outcomes through customers’ decision confidence.
