From Pixels to Semantics: Edge AI for UAV-Based Critical Infrastructure Inspection
论文探讨了使用轻量级视觉语言模型在边缘设备上实现无人机基础设施检查，从物体检测转向语义理解，以解决传统手动检查成本高和危险的问题。
0 citationsRead paper
Selected work
Representative Papers
Auditing Patient Privacy in Medical Generative Models: Scalable Memorization Detection with DeepSSIM++
为解决医学生成模型中的患者隐私泄露问题，提出DeepSSIM++方法，通过多尺度特征聚合和解剖保留增强学习嵌入空间，有效检测记忆化现象。
0 citationsRead paper
Illiquidity at Risk
研究通过引入Illiquidity-at-Risk (IlliQaR)指标并考虑跳跃成分，改进了流动性枯竭的预测方法，解决了市场流动性预测问题。
0 citationsRead paper
DRLM: Deep Reinforcement Learning-Based LLM Query Orchestration in Edge Environments
本文提出DRLM框架，利用深度强化学习解决边缘环境中大语言模型查询调度问题，通过预测器和PPO代理优化决策，减少延迟并保持准确性。
0 citationsRead paper
Beyond Component Testing: Validating Agentic AI Systems
Existing verification methods for AI agent systems struggle to assess the reliability of multi-step decision trajectories in dynamic environments. Through a systematic literature review of 257 studies, this work constructs a five-dimensional verification taxonomy encompassing behavioral, safety, temporal, regulatory, and multi-agent aspects. Analysis of case studies from healthcare, industrial automation, and intelligent transportation reveals critical gaps in current research, particularly concerning temporal validity, runtime evidence maintenance, regulatory interpretability, and assurance in open multi-agent settings. The study proposes a lifecycle-oriented verification agenda and outlines four key directions: bounded autonomy specifications, adversarial trajectory generation, runtime monitoring, and auditable evidence structures—collectively offering a pathway toward context-aware, trajectory-level trustworthy verification.
0 citationsRead paper
Recent publications
Latest Papers
From Pixels to Semantics: Edge AI for UAV-Based Critical Infrastructure Inspection
论文探讨了使用轻量级视觉语言模型在边缘设备上实现无人机基础设施检查，从物体检测转向语义理解，以解决传统手动检查成本高和危险的问题。
0 citationsRead paper
Auditing Patient Privacy in Medical Generative Models: Scalable Memorization Detection with DeepSSIM++
为解决医学生成模型中的患者隐私泄露问题，提出DeepSSIM++方法，通过多尺度特征聚合和解剖保留增强学习嵌入空间，有效检测记忆化现象。
0 citationsRead paper
Illiquidity at Risk
研究通过引入Illiquidity-at-Risk (IlliQaR)指标并考虑跳跃成分，改进了流动性枯竭的预测方法，解决了市场流动性预测问题。
0 citationsRead paper
DRLM: Deep Reinforcement Learning-Based LLM Query Orchestration in Edge Environments
本文提出DRLM框架，利用深度强化学习解决边缘环境中大语言模型查询调度问题，通过预测器和PPO代理优化决策，减少延迟并保持准确性。
0 citationsRead paper
Beyond Component Testing: Validating Agentic AI Systems
Existing verification methods for AI agent systems struggle to assess the reliability of multi-step decision trajectories in dynamic environments. Through a systematic literature review of 257 studies, this work constructs a five-dimensional verification taxonomy encompassing behavioral, safety, temporal, regulatory, and multi-agent aspects. Analysis of case studies from healthcare, industrial automation, and intelligent transportation reveals critical gaps in current research, particularly concerning temporal validity, runtime evidence maintenance, regulatory interpretability, and assurance in open multi-agent settings. The study proposes a lifecycle-oriented verification agenda and outlines four key directions: bounded autonomy specifications, adversarial trajectory generation, runtime monitoring, and auditable evidence structures—collectively offering a pathway toward context-aware, trajectory-level trustworthy verification.
0 citationsRead paper