Search Results (354)

Model-based reinforcement learning (MBRL) is a promising approach for achieving high sample efficiency in learning control policies. The existing world models in MBRL typically represent the environment’s state as a single global latent vector. However, such representations limit the model’s ability to capture object interactions and reason about individual objects—capabilities that are critical for visual object-oriented tasks—and may lead to lower sample efficiency. To address this limitation, we propose Kuramoto Object-Centric Reinforcement Learning (KORL), a model-based agent that learns an object-centric world model. Our approach introduces a novel Kuramoto Slot Attention for Video (KSAVi) model that integrates Kuramoto oscillatory neurons with the Slot Attention module to robustly extract object representations. We design a world model that leverages these structured object-centric latents and predicts dynamics using graph neural networks, thereby incorporating an inductive bias for modeling object interactions. We evaluate KORL on a suite of visually diverse object-oriented robotic manipulation tasks and demonstrate that our method outperforms object-centric model-free and model-based approaches. Full article

To address the limitations of zero-shot generalization in Vision-Language Navigation (VLN), this paper proposes a novel knowledge graph-driven reinforcement learning approach. Our method constructs a hierarchical, dynamically updated knowledge graph online during the agent’s real-time interaction with the environment, seamlessly aligning external semantic priors with continuous visual perception. By leveraging a Chain-of-Thought (CoT) prompting mechanism, the agent performs multi-hop reasoning to precisely locate target objects. Furthermore, we design an end-to-end optimized reinforcement learning framework that fuses multi-modal features and employs a task-oriented composite reward function. Extensive experiments in the AI2-THOR simulation environment demonstrate that the proposed method significantly improves navigation success rates in zero-shot settings. The results validate its robust generalization capabilities, particularly for unseen object categories and complex scene layouts. Full article

Deep-learning-based vulnerability detection has made substantial progress, but two limitations remain prominent. Sequence-based methods linearize source code and thus weaken the explicit modeling of control-flow and data-flow dependencies. Graph-based methods preserve program structure, yet conventional graph neural networks still have difficulty capturing long-range interactions in large code property graphs (CPGs). In addition, standard CPGs usually lack explicit variable semantics and security-critical node roles, which limits their ability to represent vulnerability-relevant program behavior. To address these issues, we propose SV-GEN, a vulnerability detection framework that combines large-language-model-driven semantic enhancement with hybrid sequence-graph learning. The novelty of SV-GEN lies in introducing a semantically enriched code property graph, termed Sem-CPG, which augments conventional CPGs with variable semantic roles and security-oriented node labels, and in coupling this representation with an adaptive fusion mechanism over structural and sequential views. Specifically, we use a large language model as an external semantic annotator to assign variable roles and identify source, sink, and sanitizer nodes, and then encode the resulting Sem-CPG with a Graph Transformer while modeling the code sequence with GraphCodeBERT. A learnable gating module is further used to adaptively fuse the graph-level and sequence-level representations for final prediction. Experiments on Devign, ReVeal, and DiverseVul show that SV-GEN achieves competitive or superior overall performance across benchmarks, with particularly strong improvements on the large and highly imbalanced DiverseVul dataset. Full article

This paper presents a data-driven surrogate model for predicting cabin airflow and its integration into system-level electric vehicle simulations for energy management analysis. The model employs a graph-based neural network with a mirror-symmetric predictor–corrector architecture and is trained on a dataset generated using computational fluid dynamics (CFD) covering a defined range of inlet velocities and temperatures. The surrogate appropriately reconstructs temperature fields and captures the dominant airflow structures at significantly lower computational cost than CFD. Quantitative evaluation shows high accuracy in passenger-relevant regions, while localized discrepancies remain confined mainly to shear-layer zones. The model enables near-real-time inference and is coupled with a system-level modeling framework for control-oriented simulations that are impractical with CFD. The study is tailored to a specific geometry and operating range, showing that targeted training strategies and physics-based extensions improve robustness, particularly under limited data conditions. Full article

Indoor localization in GNSS-denied environments remains a significant challenge due to the low sampling frequency and high variability of wireless signal measurements. This~paper presents a wireless communication-based indoor localization method that integrates Wi-Fi received signal strength indication (RSSI) measurements with optical initialization and inertial sensor fusion. The proposed approach eliminates the need for labor-intensive fingerprinting and specialized infrastructure by leveraging existing Wi-Fi networks. Optical pose estimation using ArUco markers provides accurate initial position and orientation, enabling alignment between sensor coordinate systems and reducing inertial drift. During tracking, inertial measurements compensate for motion between sparse Wi-Fi observations by virtually translating historical RSSI samples, allowing statistically consistent averaging and improved distance estimation. A simplified factor graph framework is employed to fuse heterogeneous measurements while maintaining computational efficiency suitable for real-time operation on mobile devices. Experimental validation using a robot-based ground-truth reference system demonstrates sub-meter localization accuracy with an average positioning error of approximately 0.40~m. The proposed method provides a low-cost and scalable solution for indoor positioning and navigation applications such as access-controlled environments, exhibitions, and large public venues. Full article

Autonomous task assignment in multi-unmanned aerial vehicle (UAV) systems operating in dynamic and safety-critical airspace environments is highly challenging due to complex spatial interactions and rapidly changing relative geometries. This paper proposes a hierarchical decision-making framework that bridges individual maneuvering behaviors with cooperative task allocation in multi-agent aerial systems. First, a high-fidelity single-agent maneuver model is learned using a physics-consistent simulation environment, where spatial advantage is evaluated based on relative distance and angular relationships within a kinematically feasible interaction zone (KIZ). Subsequently, a Geometry-Aware Graph Attention Network (GA-GAT) is developed to address scalable multi-agent assignment problems. Unlike conventional approaches that rely on flat feature representations, the proposed method explicitly incorporates kinematic feasibility constraints into the attention mechanism via a novel gating module, enabling efficient relational reasoning under dynamic conditions. The proposed framework is applicable to a range of civilian and safety-oriented scenarios, including UAV swarm coordination, emergency response monitoring, infrastructure inspection, and autonomous airspace management. Simulation results demonstrate that the GA-GAT-based approach significantly outperforms heuristic baselines in terms of coordination efficiency and overall system performance in complex multi-agent environments. This study highlights that decoupling maneuver-level control from high-level coordination provides a scalable and computationally efficient solution for real-time multi-UAV decision-making in safety-critical applications. The proposed framework is designed for general multi-agent coordination problems in civilian aerial applications. Full article

Planar multi-loop mechanisms often generate a large number of non-isomorphic candidate topological graphs during automatic synthesis, making it difficult to efficiently identify configurations that satisfy engineering-oriented functional requirements. To address this issue, a loop-constrained connectivity calculation method and a connectivity-based localization and screening procedure are proposed. The proposed connectivity calculation is directly formulated for general planar non-fractionated kinematic chains (NFKCs), including those with multiple joints. For planar fractionated kinematic chains (FKCs), however, the present method is not applied directly at the full-system level, but only to decomposed non-fractionated subchains after system-level decomposition. Starting from a structurally admissible set of candidate topological graphs, a connectivity matrix is established for automatic localization of the base and the end-effector (EE). Functional screening is then performed by combining the connectivity criterion with object-oriented rules on hydraulic driving-pair arrangement and driving-redundancy patterns. The method was validated using the 10-link, 3-DOF single-joint equivalent of the KC1 subchain of a mine scaler manipulator arm. Under the prescribed structural and functional constraints, 249 admissible configurations were obtained. The results indicate that the proposed method provides an effective basis for application-oriented topological screening and subsequent dimensional synthesis. Full article

Equity-aware electric vehicle (EV) charging planning remains difficult in data-constrained cities. In this work, an integrated framework was developed by combining spatiotemporal graph neural networks (ST-GNNs), EVI-Pro Lite demand estimation, and lexicographic bi-level optimization, and was applied to Bogotá, Colombia (8.3 million inhabitants). Household travel survey data (12,500 households across 142 zones) were used to estimate zone-level priority scores and venue-specific temporal weights. EVI-Pro Lite simulations projected a 2025 requirement of 10,870 charging ports (7352 residential, 2739 workplace, and 779 public). In the allocation stage, Level 1 preserved priority-proportional targets, while Level 2 minimized inter-zonal inequality in Hansen accessibility subject to near-optimal Level-1 compliance. The final allocation retained strong priority alignment in installed ports (Spearman $\rho =0.799$, $p<{10}^{-31}$), while the priority–accessibility association was lower (Spearman $\rho =0.320$, $p=1.04\times {10}^{-4}$), consistent with second-stage equity redistribution. Equity outcomes also improved (Hansen Gini = 0.433; bottom-50% Lorenz share = 0.204). The mean Hansen accessibility reached 296.630 (standard deviation 248.099; minimum 1.126). These findings indicate that reproducible, equity-oriented EV infrastructure plans can be produced in cities where revealed charging microdata are limited. Full article

Trajectory planning in dynamic multi-vehicle interaction environments faces three critical challenges, including the difficulty of quantifying spatial risk distributions, the complexity of characterizing behavioral uncertainty arising from the multimodal maneuvers of surrounding vehicles, and the challenge of simultaneously optimizing multiple competing objectives such as safety, efficiency, comfort, and energy consumption. To address these challenges, this paper proposes an Improved Driving Risk Field-based Multi-objective Trajectory Optimization (IDRF-MTO) method. First, a joint spatiotemporal social attention mechanism achieves unified modeling of spatial interactions, temporal dependencies, and spatiotemporal coupling, combined with a lateral–longitudinal intent strategy for multimodal trajectory prediction. Second, an improved dynamic risk field model is constructed comprising three components: a vehicle risk field that incorporates spatial orientation and motion direction factors for anisotropic risk representation, along with a collision tendency factor that converts objective risk into effective risk; a predicted trajectory risk field that achieves anticipatory quantification of future risk from surrounding vehicles through confidence-weighted fusion; and a driving environment risk field that encapsulates road geometry, static obstacles, and environmental conditions. Finally, a multi-objective cost function embedding risk field gradients is formulated, and multi-objective coordinated optimization is realized through a three-dimensional spatiotemporal situation graph with adaptive safety sampling. Simulation results demonstrate that the proposed method enhances safety while simultaneously improving comfort and efficiency and reducing energy consumption, exhibiting excellent planning performance in complex dynamic environments. Full article

This study aims to identify and synthesize the major global trends that shaped 2025 by applying the DeflyCompass methodology to a curated corpus of strategic foresight reports. The study synthesizes insights from 23 strategic reports published by leading international organizations, including the World Economic Forum, Accenture, Euromonitor, and major technology firms. Methodologically, DeflyCompass operationalizes a structured hybrid human–AI pipeline comprising the deployment of multi-agent AI systems, automated knowledge graph construction, semantic clustering, and hybrid human–AI validation processes, reducing an initial set of 816 preliminary signals to a validated catalog of 50 high-priority trends across six PESTEL domains: Political, Economic, Social, Technological, Environmental, and Legal/Governance. Key findings indicate that artificial intelligence functions as a systemic enabling technology across all domains, climate and sustainability imperatives permeate multiple domains, geopolitical fragmentation introduces systemic tension, and trust deficits emerge as a critical vulnerability. The study contributes a replicable and scalable framework for global-level strategic foresight that operationalizes human–AI integration within a rigorous expert-driven validation process, complementing existing hybrid analytical approaches in the literature. Implications extend to decision-making in technology governance, sustainability strategy, social adaptation, and scenario planning, highlighting the necessity of integrating AI augmentation with human expertise for effective future-oriented planning. Full article

In this study, we examined how disinformation and trustworthy news differ in their narrative construction across nine theoretically motivated dimensions. We address the following research question: how do disinformation and trustworthy news differ in narrative organisation and epistemic grounding? We analysed 610 English-language news articles (308 pro-Kremlin disinformation and 302 trustworthy articles) covering selected international events from 2015 to 2023, using data derived from the EUvsDisinfo dataset. Narrative elements were extracted using a hybrid pipeline combining large language models and knowledge graphs, resulting in article-level representations for comparative analysis. Ordinal scores (1–5) were assigned for emotional intensity, cultural complexity, conspiracist structure, source diversity, crisis intensity, evidence support, media control, solutions orientation and memory work. Non-parametric comparisons showed significant differences in eight of these nine dimensions. Disinformation articles revealed stronger conspiracist structuring and greater meta-media hostility, as well as significantly lower source diversity, evidence support, cultural complexity and weaker memory work. Emotional intensity did not differ reliably across disinformation and trustworthy news. A simple additive NarrativeRisk score, which we designed as a transparent and interpretable summary measure, showed between-group differences in both parametric and non-parametric tests. As a univariate discrimination indicator, NarrativeRisk achieved ROC AUC ≈ 0.84. Cluster analysis identified three recurrent narrative profiles, including one dominated by disinformation, one by trustworthy news and one mixed profile. These findings indicate that disinformation is distinguished not only by factual unreliability but also by different patterns in narrative organisation. Full article

Balancing ecological protection, carbon sinks, and development is a practical challenge in mountainous regions. Using Yunnan Province, China, as a case study, this paper develops a knowledge-guided probabilistic framework for carbon-oriented territorial zoning. The framework combines an indicator system, corridor analysis of pattern, risk and potential, knowledge-graph rule encoding, Bayesian mechanism calibration, and constrained posterior decoding on 11,853 effective planning cells. The results show a clear conservation–development gradient in the carbon sink priority surface: high-priority areas are concentrated in western and southwestern Yunnan, whereas low-priority areas cluster around major urban centers. Corridor analysis identifies a central resistance belt and several urban–rural bottlenecks, indicating that connectivity constraints are concentrated in a limited number of critical links. The final zoning assigns 35.4% of grids to integrated development, 25.9% to emergency intervention, 14.5% to long-term conservation, 13.8% to priority restoration, and 10.4% to risk control. Zone separability is generally strong, with one-versus-rest AUC values ranging from 0.777 to 0.995. Land use enrichment further supports the zoning results: integrated development contains 78.85% of built-up land and 45.93% of cropland, whereas Emergency intervention, priority restoration, and long-term conservation together contain 70.01% of forest area. Full article

Large language models (LLMs) have been widely applied to knowledge graph question answering (KGQA) systems. Recent Text-to-SPARQL studies have demonstrated that generation performance can achieve an F1 score exceeding 90%. Further error analysis has categorized common errors into entity translation errors, entity position errors, and resource description framework (RDF) triple-count errors, with the latter accounting for 24% of all errors. Notably, nearly 90% of RDF triple-count errors occur when the triples involve class entities. Previous research has shown that incorporating prompts can effectively enhance model performance. Based on the results, we predicted whether a question contains a class entity and the number of RDF triples in the corresponding query to reduce RDF triple-count errors in large language models by providing precise task-related information through prompt design. Since both strategies are classification-oriented, two implementation paradigms were established: traditional classification architectures and generative modeling. They were compared in terms of performance. For classification-based architectures, we employed Bidirectional Encoder Representations from Transformers (BERT) and the Robustly Optimized BERT Approach (RoBERTa) to obtain question embeddings for classification. For the generative approach, we adopted the Instruction-Tuned Text-to-Text Transfer Transformer (Flan-T5). Experimental results show that the generative model slightly outperforms conventional classification architectures, indicating that generative approaches can achieve higher prediction accuracy and provide more reliable information without the need for additional complex encoder designs, thereby improving the overall quality of Text-to-SPARQL generation. Full article

The development of novel antiepileptic agents requires early identification of pharmacokinetic limitations to mitigate risks at later stages. This study aimed to perform in silico profiling of a library containing 448 novel 2H,5H-chromeno[4’,3’:4,5]thiopyrano[2,3-d]thiazol-2-one derivatives to select lead compounds with an optimal balance of safety and efficacy. The study was conducted using the ADMET-AI platform, based on a graph neural network, to predict physicochemical, pharmacokinetic, and toxicological properties. The methodology involved calculating drug-likeness descriptors for primary screening and a comparative statistical analysis of the top 20 selected structures against 16 approved antiepileptic drugs and four reference compounds. Based on drug-likeness descriptors and predicted ADMET (absorption, distribution, metabolism, excretion, toxicity) related parameters, 20 structures were prioritized for further analysis. Their predicted profiles suggested high intestinal absorption and blood–brain barrier (BBB) permeability, which may be relevant for central nervous system (CNS) directed agents. In comparison with the reference thiazolidinones, the prioritized compounds showed comparatively more favorable predicted mutagenicity and carcinogenicity profiles. Elevated predicted risks of hepatotoxicity and cardiotoxicity were observed for several structures, indicating the need for further structural optimization. The results suggest that the thiopyranothiazolidinone scaffold merits further anticonvulsant-oriented investigation at the stage of early compound prioritization. Experimental validation will be required to confirm the actual pharmacokinetic, toxicological, and anticonvulsant properties of the prioritized compounds. Full article

Accurate modeling of learners’ evolving cognitive states is essential for intelligent educational systems, yet many existing knowledge tracing and graph-based approaches rely on static structures or purely sequential representations that inadequately capture dynamic structural changes in learning processes. This study proposes a Learner Cognitive Graph (LCG) framework that integrates dynamic heterogeneous graph modeling, structured behavioral data acquisition, and reinforcement learning-based intervention optimization. A Dynamic Cognition Graph (DCG) is formally defined as a sequence of temporally evolving graph snapshots representing interactions among learners, knowledge concepts, and exercises. A reverse Turing test-based agent with structured prompting is introduced to collect reasoning-oriented behavioral evidence, improving data reliability for cognitive modeling. Temporal message passing, multi-scale memory updating, and self-supervised learning objectives are employed to construct dynamic cognitive representations. Personalized intervention is formulated as a Markov decision process to optimize long-term learning outcomes. Experiments conducted on real-world and simulated educational datasets demonstrate improved knowledge mastery prediction accuracy, cognitive state transition modeling, and intervention efficiency compared with representative baselines. The proposed framework provides a systematic and scalable approach for dynamic cognitive modeling and adaptive educational support. Full article