arXiv subjects

Wei Meng

Publications and source records attributed to Wei Meng.

At least 19 recordsLinked to original sources

arXiv2026

ForeSightGuide: An Anticipatory Framework toward Accurate and Low-Redundancy Guidance for the Visually Impaired

Electronic travel aids are pivotal for the independent mobility of the visually impaired. While Vision-Language Models (VLMs) offer rich environmental understanding, they often suffer from excessive false positives in dynamic scenarios, leading to cognitive overload. To address this, we present ForeSightGuide, an anticipatory assistive guidance framework that couples semantic scene understanding with predictive hazard assessment. Unlike reactive systems, ForeSightGuide leverages the reasoning capabilities of VLMs to anticipate obstacle motion, effectively filtering out non-threatening objects to provide concise, actionable guidance. To validate our approach, we introduce a novel dataset captured in complex, dynamic real-world traffic scenes, designed to benchmark predictive capabilities. Extensive experiments on both public benchmarks and our proposed dataset demonstrate that ForeSightGuide achieves state-of-the-art performance. Notably, it significantly mitigates information overload by reducing redundant alerts to 0.299 per guidance output while maintaining a low missed-hazard rate of 0.112, proving its efficacy for safe walking assistance.

cs.CV↗

arXiv2026

Programming-by-Example for Batch-Editing Collision Meshes in 3D Software

As 3D software proliferates, software artifacts now extend beyond code and 2D user interfaces to include 3D assets. Among these assets, collision meshes are critical as they define the geometry used by physics engines for collision detection and physical interaction. Although existing tools can automatically generate collision meshes from visual meshes, they often fail to capture the intended interaction behavior. As a result, developers need to manually edit many heterogeneous collision meshes, a process that is time-consuming and challenging to scale. To address this problem, we present a neuro-symbolic program synthesis approach for batch-editing collision meshes. We formulate the task as a programming-by-example problem: given a family of collision meshes with the same editing intent and a small number of user demonstrations, our approach synthesizes a reusable program that captures the editing intent and applies it to non-demonstration meshes. We implement this in a tool named MeshForge, and evaluate it across 24 tasks on 600 collision meshes. MeshForge successfully synthesizes 23/24 tasks, requiring 2.2 demonstrations and 3.5 seconds of synthesis time on average.

cs.GR↗

arXiv2026

Characterizing Finite Groups via Subgroup Perfect Codes

A perfect code in a graph $\Gamma = (V, E)$ is a subset $C$ of $V$ such that no two vertices in $C$ are adjacent and every vertex in $V \setminus C$ is adjacent to exactly one vertex in $C$. A subgroup $H$ of a group $G$ is called a subgroup perfect code of $G$ if it is a perfect code in some Cayley graph of $G$. In this paper, we study the set $\Delta(G)$ of conjugacy classes of nontrivial subgroup perfect codes of $G$, with a focus on its relation to $|\pi(G)|$, the number of prime divisors of $|G|$. We prove that $|\Delta(G)| \ge |\pi(G)|$ with only three exceptional families, which leads to the natural question: when is this bound attained or nearly attained? We completely classify finite groups $G$ satisfying $|\Delta(G)| = |\pi(G)|$ and $|\Delta(G)| = |\pi(G)| + 1$, and we further characterize all insolvable groups with $|\Delta(G)| \le 6$. Our approach is based on the classification of primitive groups of odd degree, as well as the classification of primitive groups of square-free degree.

math.CO↗

arXiv2026

Cross-subject Muscle Fatigue Detection via Adversarial and Supervised Contrastive Learning with Inception-Attention Network

Muscle fatigue detection plays an important role in physical rehabilitation. Previous researches have demonstrated that sEMG offers superior sensitivity in detecting muscle fatigue compared to other biological signals. However, features extracted from sEMG may vary during dynamic contractions and across different subjects, which causes unstability in fatigue detection. To address these challenges, this research proposes a novel neural network comprising an Inception-attention module as a feature extractor, a fatigue classifier and a domain classifier equipped with a gradient reversal layer. The integrated domain classifier encourages the network to learn subject-invariant common fatigue features while minimizing subject-specific features. Furthermore, a supervised contrastive loss function is also employed to enhance the generalization capability of the model. Experimental results demonstrate that the proposed model achieved outstanding performance in three-class classification tasks, reaching 93.54% accuracy, 92.69% recall and 92.69% F1-score, providing a robust solution for cross-subject muscle fatigue detection, offering significant guidance for rehabilitation training and assistance.

cs.LG↗

arXiv2026

ComBench: A Repo-level Real-world Benchmark for Compilation Error Repair

Compilation errors pose pervasive and critical challenges in software development, significantly hindering productivity. Therefore, Automated Compilation Error Repair (ACER) techniques are proposed to mitigate these issues. Despite recent advancements in ACER, its real-world performance remains poorly evaluated. This can be largely attributed to the limitations of existing benchmarks, \ie decontextualized single-file data, lack of authentic source diversity, and biased local task modeling that ignores crucial repository-level complexities. To bridge this critical gap, we propose ComBench, the first repository-level, reproducible real-world benchmark for C/C++ compilation error repair. ComBench is constructed through a novel, automated framework that systematically mines real-world failures from the GitHub CI histories of large-scale open-source projects. Our framework contributes techniques for the high-precision identification of ground-truth repair patches from complex version histories and a high-fidelity mechanism for reproducing the original, ephemeral build environments. To ensure data quality, all samples in ComBench are execution-verified -- guaranteeing reproducible failures and build success with ground-truth patches. Using ComBench, we conduct a comprehensive evaluation of 12 modern LLMs under both direct and agent-based repair settings. Our experiments reveal a significant gap between a model's ability to achieve syntactic correctness (a 73% success rate for GPT-5) and its ability to ensure semantic correctness (only 41% of its patches are valid). We also find that different models exhibit distinct specializations for different error types. ComBench provides a robust and realistic platform to guide the future development of ACER techniques capable of addressing the complexities of modern software development.

cs.SE↗

arXiv2026

On the number of non-cyclic subgroups of finite p-groups

Let $G$ be a finite $p$-group and $\delta(G)$ denote the number of all non-cyclic subgroups of $G$. In this paper, an upper bound for $\delta(G)$ is obtained. Furthermore, we prove that $\delta(G)\leq \delta(M_p(1, 1, 1) \times C_{p}^{n-3})$ (if $p=2$, then $\delta(G)\leq \delta(D_8\times C_{2}^{n-3})$), for any non-elementary abelian $p$-group $G$ of order $p^n$.

math.GR↗

arXiv2026

On SS-quasinormalities of the maximal subgroup series of finite groups

Let $G$ be finite group. A subgroup $H$ of $G$ is said to be an $SS$-quasinormal subgroup of $G$, if there exists a subgroup $B$ of $G$ such that $G = HB$ and $H$ permutes with every Sylow subgroup of $B$. Let $\Omega: G=G_0>G_1>\cdots>G_{n-1}>G_n=1$ be a maximal subgroup series of $G$, where $G_i$ is a maximal subgroup of $G_{i-1}$ for every $i = 1, \ldots , n$. In this paper, we investigate the finite groups $G$ that admit an $SS$-quasinormal maximal subgroup series, i.e., all $G_i$ are $SS$-quasinormal in $G$. First, we prove that if $G$ possesses an $SS$-quasinormal maximal subgroup series, then $G$ is solvable. Furthermore, we show that $G$ is supersolvable if and only if $G$ possesses an $SS$-quasinormal maximal subgroup series which is subnormal in $G$.

math.GR↗

arXiv2026

Wukong-Omni: Design, Modeling and Control of a Multi-mode Robot for Air, Land, and Underwater Exploration with All-in-One Propulsion Unit

In flood disaster rescue scenarios, partially submerged buildings prevent aerial robots from accessing lower levels, limiting mission effectiveness. To address this challenge, this paper presents Wukong-Omni, a novel multimode robot capable of operating across land, air, and underwater using a unified propulsion system. The system is enabled by an innovative mechanical design that allows motor reuse and improves thrust generation. Efficiency and peak thrust are enhanced through simulation and tank-based optimization. Experimental results show a 100 percent improvement in propulsion efficiency and a 150 percent increase in maximum thrust compared with direct installation methods. Dynamic models for the three operating domains are developed, and a unified cross-domain control framework is proposed. Comprehensive experiments validate stable locomotion and smooth transition across domains. Outdoor experiments further demonstrate robustness and adaptability in real-world environments.

cs.RO↗

arXiv2025

Computable Gap Assessment of Artificial Intelligence Governance in Children's Centres: Evidence-Mechanism-Governance-Indicator Modelling of UNICEF's Guidance on AI and Children 3.0 Based on the Graph-GAP Framework

This paper tackles practical challenges in governing child centered artificial intelligence: policy texts state principles and requirements but often lack reproducible evidence anchors, explicit causal pathways, executable governance toolchains, and computable audit metrics. We propose Graph-GAP, a methodology that decomposes requirements from authoritative policy texts into a four layer graph of evidence, mechanism, governance, and indicator, and that computes two metrics, GAP score and mitigation readiness, to identify governance gaps and prioritise actions. Using the UNICEF Innocenti Guidance on AI and Children 3.0 as primary material, we define reproducible extraction units, coding manuals, graph patterns, scoring scales, and consistency checks, and we demonstrate exemplar gap profiles and governance priority matrices for ten requirements. Results suggest that compared with privacy and data protection, requirements related to child well being and development, explainability and accountability, and cross agency implementation and resource allocation are more prone to indicator gaps and mechanism gaps. We recommend translating requirements into auditable closed loop governance that integrates child rights impact assessments, continuous monitoring metrics, and grievance redress procedures. At the coding level, we introduce a multi algorithm review aggregation revision workflow that runs rule based encoders, statistical or machine learning evaluators, and large model evaluators with diverse prompt configurations as parallel coders. Each extraction unit outputs evidence, mechanism, governance, and indicator labels plus readiness scores with evidence anchors. Reliability, stability, and uncertainty are assessed using Krippendorff alpha, weighted kappa, intraclass correlation, and bootstrap confidence intervals.

cs.CY↗

arXiv2025

Improving Low-Latency Learning Performance in Spiking Neural Networks via a Change-Perceptive Dendrite-Soma-Axon Neuron

Spiking neurons, the fundamental information processing units of Spiking Neural Networks (SNNs), have the all-or-zero information output form that allows SNNs to be more energy-efficient compared to Artificial Neural Networks (ANNs). However, the hard reset mechanism employed in spiking neurons leads to information degradation due to its uniform handling of diverse membrane potentials. Furthermore, the utilization of overly simplified neuron models that disregard the intricate biological structures inherently impedes the network's capacity to accurately simulate the actual potential transmission process. To address these issues, we propose a dendrite-soma-axon (DSA) neuron employing the soft reset strategy, in conjunction with a potential change-based perception mechanism, culminating in the change-perceptive dendrite-soma-axon (CP-DSA) neuron. Our model contains multiple learnable parameters that expand the representation space of neurons. The change-perceptive (CP) mechanism enables our model to achieve competitive performance in short time steps utilizing the difference information of adjacent time steps. Rigorous theoretical analysis is provided to demonstrate the efficacy of the CP-DSA model and the functional characteristics of its internal parameters. Furthermore, extensive experiments conducted on various datasets substantiate the significant advantages of the CP-DSA model over state-of-the-art approaches.

cs.NE↗

arXiv2025

Monte Carlo simulation of the Compton scattering and disk reflection of a cylinder with hot electrons moving away from a black hole

For accreting black holes (BHs), the lamp-post scenario is a simple and popular model: a hot and point-like corona is located above the black hole, irradiating the accretion disk with hard X-ray radiation, which is believed to be generated by inverse Compton scattering in the corona. Although the lamp-post model successfully explains the disk reflection component, it fails to address the origin of seed photons and the geometry of the hot corona, because this model simplistically treats the corona as a point-like source generating a cutoff powerlaw spectrum. In this paper, we make simulations on a possible physical realization of the lamp-post scenario: the shape of the scattering zone is set to be a cylinder, corresponding to the jet base near a BH. The source of seed photons in this system is assumed to be the multicolor blackbody radiation of the accretion disk. In our simulations, the Compton scattering process is simulated with a custom Monte Carlo program based on the Geant4 package and the disk reflection process is simulated with the xilconv model in XSPEC. Our simulation results have confirmed that the relativistic motion of the jet can weaken or even completely suppress the reflection of the accretion disk, and simultaneously, the Comptonization of disk photons in the jet can still make a major contribution to the observed X-ray spectrum in high energy range. We discuss the implications of our simulation results, in light of the recent observations of a very weak reflection component in the presence of a strong hard X-ray radiation from the outburst of Swift J1727.8-1613.

astro-ph.HE↗

arXiv2025

2025 Southeast Asia Eleven Nations Influence Index Report

This study constructs a fully data-driven and reproducible Southeast Asia Influence Index (SAII v3) to reduce bias from expert scoring and subjective weighting while mapping hierarchical power structures across the eleven ASEAN nations. We aggregate authoritative open-source indicators across four dimensions (economic, military, diplomatic, socio-technological) and apply a three-tiered standardization chain quantile-Box-Cox-min-max to mitigate outliers and skewness. Weights are obtained through equal-weight integration of Entropy Weighting Method (EWM), CRITIC, and PCA. Robustness is assessed via Kendall's tau, +/-20% weight perturbation, and 10,000 bootstrap iterations, with additional checks including +/-10% dimensional sensitivity and V2-V3 bump chart comparisons. Results show integrated weights: Economy 35-40%, Military 20-25%, Diplomacy about 20%, Socio-Technology about 15%. The regional landscape exhibits a one-strong, two-medium, three-stable, and multiple-weak pattern: Indonesia, Singapore, and Malaysia lead, while Thailand, the Philippines, and Vietnam form a mid-tier competitive band. V2 and V3 rankings are highly consistent (Kendall's tau = 0.818), though small mid-tier reorderings appear (Thailand and the Philippines rise, Vietnam falls), indicating that v3 is more sensitive to structural equilibrium. ASEAN-11 average sensitivity highlights military and socio-technological dimensions as having the largest marginal effects (+/-0.002). In conclusion, SAII v3 delivers algorithmic weighting and auditable reproducibility, reveals multidimensional drivers of influence in Southeast Asia, and provides actionable quantitative evidence for resource allocation and policy prioritization by regional governments and external partners.

physics.soc-ph↗

arXiv2025

Aerial Target Encirclement and Interception with Noisy Range Observations

This paper proposes a strategy to encircle and intercept a non-cooperative aerial point-mass moving target by leveraging noisy range measurements for state estimation. In this approach, the guardians actively ensure the observability of the target by using an anti-synchronization (AS), 3D ``vibrating string" trajectory, which enables rapid position and velocity estimation based on the Kalman filter. Additionally, a novel anti-target controller is designed for the guardians to enable adaptive transitions from encircling a protected target to encircling, intercepting, and neutralizing a hostile target, taking into consideration the input constraints of the guardians. Based on the guaranteed uniform observability, the exponentially bounded stability of the state estimation error and the convergence of the encirclement error are rigorously analyzed. Simulation results and real-world UAV experiments are presented to further validate the effectiveness of the system design.

cs.RO↗

arXiv2025

AR-LIF: Adaptive reset leaky integrate-and-fire neuron for spiking neural networks

Spiking neural networks offer low energy consumption due to their event-driven nature. Beyond binary spike outputs, their intrinsic floating-point dynamics merit greater attention. Neuronal threshold levels and reset modes critically determine spike count and timing. Hard reset cause information loss, while soft reset apply uniform treatment to neurons. To address these issues, we design an adaptive reset neuron that establishes relationships between inputs, outputs, and reset, while integrating a simple yet effective threshold adjustment strategy. Experimental results demonstrate that our method achieves excellent performance while maintaining lower energy consumption. In particular, it attains state-of-the-art accuracy on Tiny-ImageNet and CIFAR10-DVS. Codes are available at https://github.com/2ephyrus/AR-LIF.

cs.NE↗

arXiv2025

Algorithmic Evaluation and the Marginalization of Single Authorship in Management Science

The decline of single authorship in peer-reviewed journals within the current collaboration-oriented knowledge production framework has prompted deeper reflection on the shifting power structures in academic systems. This paper aims to explore the underlying institutional logic and evaluation mechanisms contributing to the marginalization of single-author research in the management field. It further investigates how the discourse of collaborative advantage conceals structural power redistribution and ideological disembedding. Through an analysis of authorship data from top-tier journals, a critical reading of institutional incentive texts, and an empirical review of authorial configurations, the study building on the work of Harzing, Wuchty, and Lariviere constructs a three-dimensional causal chain: collaboration incentives, responsibility dilution, and originality weakening. Findings suggest that single authorship is not explicitly excluded but is gradually sidelined from central publication channels by funding policies, review practices, and performance metrics. Independent thought is thus structurally marginalized within institutionalized collaboration. The paper advocates for a paradigm shift from instrumental rationality to value-based rationality and calls for the restoration of legitimacy and public value for independent research through reforms in evaluation frameworks, journal governance, and research ethics, aiming to safeguard academic diversity and intellectual autonomy.

cs.DL↗

arXiv2025

A Tactical Behaviour Recognition Framework Based on Causal Multimodal Reasoning: A Study on Covert Audio-Video Analysis Combining GAN Structure Enhancement and Phonetic Accent Modelling

This paper introduces TACTIC-GRAPHS, a system that combines spectral graph theory and multimodal graph neural reasoning for semantic understanding and threat detection in tactical video under high noise and weak structure. The framework incorporates spectral embedding, temporal causal edge modeling, and discriminative path inference across heterogeneous modalities. A semantic-aware keyframe extraction method fuses visual, acoustic, and action cues to construct temporal graphs. Using graph attention and Laplacian spectral mapping, the model performs cross-modal weighting and causal signal analysis. Experiments on TACTIC-AVS and TACTIC-Voice datasets show 89.3 percent accuracy in temporal alignment and over 85 percent recognition of complete threat chains, with node latency within plus-minus 150 milliseconds. The approach enhances structural interpretability and supports applications in surveillance, defense, and intelligent security systems.

cs.CY↗

arXiv2025

Strategic Counterfactual Modeling of Deep-Target Airstrike Systems via Intervention-Aware Spatio-Causal Graph Networks

This study addresses the lack of structured causal modeling between tactical strike behavior and strategic delay in current strategic-level simulations, particularly the structural bottlenecks in capturing intermediate variables within the "resilience - nodal suppression - negotiation window" chain. We propose the Intervention-Aware Spatio-Temporal Graph Neural Network (IA-STGNN), a novel framework that closes the causal loop from tactical input to strategic delay output. The model integrates graph attention mechanisms, counterfactual simulation units, and spatial intervention node reconstruction to enable dynamic simulations of strike configurations and synchronization strategies. Training data are generated from a multi-physics simulation platform (GEANT4 + COMSOL) under NIST SP 800-160 standards, ensuring structural traceability and policy-level validation. Experimental results demonstrate that IA-STGNN significantly outperforms baseline models (ST-GNN, GCN-LSTM, XGBoost), achieving a 12.8 percent reduction in MAE and 18.4 percent increase in Top-5 percent accuracy, while improving causal path consistency and intervention stability. IA-STGNN enables interpretable prediction of strategic delay and supports applications such as nuclear deterrence simulation, diplomatic window assessment, and multi-strategy optimization, providing a structured and transparent AI decision-support mechanism for high-level policy modeling.

cs.LG↗

arXiv2025

Modeling and Visualization Reasoning for Stakeholders in Education and Industry Integration Systems: Research on Structured Synthetic Dialogue Data Generation Based on NIST Standards

This study addresses the structural complexity and semantic ambiguity in stakeholder interactions within the Education-Industry Integration (EII) system. The scarcity of real interview data, absence of structured variable modeling, and lack of interpretability in inference mechanisms have limited the analytical accuracy and policy responsiveness of EII research. To resolve these challenges, we propose a structural modeling paradigm based on the National Institute of Standards and Technology (NIST) synthetic data quality framework, focusing on consistency, authenticity, and traceability. We design a five-layer architecture that includes prompt-driven synthetic dialogue generation, a structured variable system covering skills, institutional, and emotional dimensions, dependency and causal path modeling, graph-based structure design, and an interactive inference engine. Empirical results demonstrate the effectiveness of the approach using a 15-segment synthetic corpus, with 41,597 tokens, 127 annotated variables, and 820 semantic relationship triples. The model exhibits strong structural consistency (Krippendorff alpha = 0.83), construct validity (RMSEA = 0.048, CFI = 0.93), and semantic alignment (mean cosine similarity > 0.78 via BERT). A key causal loop is identified: system mismatch leads to emotional frustration, reduced participation, skill gaps, and recurrence of mismatch, revealing a structural degradation cycle. This research introduces the first NIST-compliant AI modeling framework for stakeholder systems and provides a foundation for policy simulation, curriculum design, and collaborative strategy modeling.

cs.CY↗