Selected work

Representative Papers

ECHO: Embodied Camera Observations of Human Object Carrying

Oct 07, 2026

This study addresses the lack of benchmarks for reasoning about natural object placement locations for embodied agents in complex environments. To this end, it introduces the contextual object placement task and constructs ECHO, the first large-scale synthetic dataset for this purpose. The proposed approach uniquely integrates RGB-D scene scans, human motion trajectories, and natural language context. By leveraging HM3D-based generation techniques, 6-DoF trajectory tracking, and input mask probes for multimodal evaluation, it establishes a novel benchmark requiring joint reasoning over scene structure and user habits. Experimental results demonstrate that no single modality suffices for this task, confirming the necessity of fusing scene structure, human activity, and contextual knowledge to achieve precise object placement.

0 citationsRead paper

When Cyber Scoring Systems Diverge: An Empirical Comparison

Sep 29, 2026

This study addresses the limitation of existing vulnerability scoring research, which predominantly focuses on statistical correlations while neglecting the practical impact on system-level risk modeling. From an operational consequence perspective, this work presents the first empirical comparative analysis of four mainstream vulnerability scoring systems, including CVSS, within a realistic Operational Technology (OT) network scenario reconstructed from the 2015 Ukrainian power grid topology. The findings reveal significant discrepancies among these systems regarding patch prioritization, demonstrating that reliance on any single scoring metric can severely misguide mitigation strategies. Accordingly, this paper advocates for the adoption of hybrid scoring methodologies, establishing a novel quantitative assessment paradigm for vulnerability risk management in critical infrastructure.

0 citationsRead paper

AI-Based Vulnerability Assessment Capability and Cyber Attack Graph Analysis

Sep 28, 2026

This study addresses the challenge of defending critical infrastructure against sophisticated cyber threats arising from complex, combinatorial attack surfaces. We propose an operational technology (OT) network risk assessment method that integrates multi-agent reinforcement learning with probabilistic attack graphs. The approach employs knowledge graphs and cross-validates findings using the Vortex/Crow framework alongside the Aalto model. Through hierarchical baseline evaluations and node elimination experiments, it precisely identifies critical targets such as industrial control systems, while risk quantification is achieved by comparing CVSS and IronMiner scoring metrics. Empirical analysis based on the Ukrainian power grid incident demonstrates that the proposed method successfully reproduces historical attack paths and exhibits strong scalability in large-scale networks. Ultimately, this work provides structured support for defense prioritization decisions in resource-constrained environments.

0 citationsRead paper

Diffusion-Induced Spatial Attention Overlapping Community Detection

Sep 22, 2026

为了解决社区检测中边界模糊和长距离依赖表示不足的问题，提出了一种结合扩散诱导空间注意力机制的深度学习框架DISCO，用于重叠社区检测。

0 citationsRead paper

The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning

Aug 04, 2026

This work addresses the insufficient reliability and trustworthiness of AI systems in high-stakes or data-scarce scenarios by proposing RAIL—a unified design framework for neuro-symbolic AI grounded in four principles: Reasoning, Assurance, Interface, and Learning. Integrating cutting-edge techniques such as physics-informed learning, causal inference, and tool-augmented large language models, RAIL offers engineers actionable design guidelines through neuro-symbolic integration, formal reasoning, and neural-guided search. The framework not only fosters deep synergy between neural and symbolic approaches but also substantially enhances AI system performance in reliability, efficiency, and trustworthiness, demonstrating broad applicability across real-world domains.

0 citationsRead paper

Recent publications

Latest Papers

ECHO: Embodied Camera Observations of Human Object Carrying

Oct 07, 2026

This study addresses the lack of benchmarks for reasoning about natural object placement locations for embodied agents in complex environments. To this end, it introduces the contextual object placement task and constructs ECHO, the first large-scale synthetic dataset for this purpose. The proposed approach uniquely integrates RGB-D scene scans, human motion trajectories, and natural language context. By leveraging HM3D-based generation techniques, 6-DoF trajectory tracking, and input mask probes for multimodal evaluation, it establishes a novel benchmark requiring joint reasoning over scene structure and user habits. Experimental results demonstrate that no single modality suffices for this task, confirming the necessity of fusing scene structure, human activity, and contextual knowledge to achieve precise object placement.

0 citationsRead paper

When Cyber Scoring Systems Diverge: An Empirical Comparison

Sep 29, 2026

This study addresses the limitation of existing vulnerability scoring research, which predominantly focuses on statistical correlations while neglecting the practical impact on system-level risk modeling. From an operational consequence perspective, this work presents the first empirical comparative analysis of four mainstream vulnerability scoring systems, including CVSS, within a realistic Operational Technology (OT) network scenario reconstructed from the 2015 Ukrainian power grid topology. The findings reveal significant discrepancies among these systems regarding patch prioritization, demonstrating that reliance on any single scoring metric can severely misguide mitigation strategies. Accordingly, this paper advocates for the adoption of hybrid scoring methodologies, establishing a novel quantitative assessment paradigm for vulnerability risk management in critical infrastructure.

0 citationsRead paper

AI-Based Vulnerability Assessment Capability and Cyber Attack Graph Analysis

Sep 28, 2026

This study addresses the challenge of defending critical infrastructure against sophisticated cyber threats arising from complex, combinatorial attack surfaces. We propose an operational technology (OT) network risk assessment method that integrates multi-agent reinforcement learning with probabilistic attack graphs. The approach employs knowledge graphs and cross-validates findings using the Vortex/Crow framework alongside the Aalto model. Through hierarchical baseline evaluations and node elimination experiments, it precisely identifies critical targets such as industrial control systems, while risk quantification is achieved by comparing CVSS and IronMiner scoring metrics. Empirical analysis based on the Ukrainian power grid incident demonstrates that the proposed method successfully reproduces historical attack paths and exhibits strong scalability in large-scale networks. Ultimately, this work provides structured support for defense prioritization decisions in resource-constrained environments.

0 citationsRead paper

Diffusion-Induced Spatial Attention Overlapping Community Detection

Sep 22, 2026

为了解决社区检测中边界模糊和长距离依赖表示不足的问题，提出了一种结合扩散诱导空间注意力机制的深度学习框架DISCO，用于重叠社区检测。

0 citationsRead paper

The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning

Aug 04, 2026

This work addresses the insufficient reliability and trustworthiness of AI systems in high-stakes or data-scarce scenarios by proposing RAIL—a unified design framework for neuro-symbolic AI grounded in four principles: Reasoning, Assurance, Interface, and Learning. Integrating cutting-edge techniques such as physics-informed learning, causal inference, and tool-augmented large language models, RAIL offers engineers actionable design guidelines through neuro-symbolic integration, formal reasoning, and neural-guided search. The framework not only fosters deep synergy between neural and symbolic approaches but also substantially enhances AI system performance in reliability, efficiency, and trustworthiness, demonstrating broad applicability across real-world domains.

0 citationsRead paper