Ready for What? Rethinking AI and Robotics Preparedness for Adoption and Policy
研究通过分析982名参与者对17个AI和机器人挑战的评估，揭示了复杂性与准备度之间的关系，强调了在政策制定中应考虑具体挑战的差异。
0 citationsRead paper
Selected work
Representative Papers
Enhancing Virtual Agents through SLMs and Edge-Computing: An Exploratory Evaluation of Think and Memory Processes
This work addresses the pressing need for embodied intelligent agents in complex virtual and metaverse environments to exhibit persistent, adaptive, and context-aware cognitive capabilities. To this end, the authors propose a lightweight edge implementation of a Cognitive Embodied Agent Architecture (CEAA), which, for the first time, integrates small language models (SLMs)—specifically the Qwen2.5 series—onto an NVIDIA Jetson Orin NX platform to form a compact cognitive “brain” endowed with perception, memory, reasoning, and action faculties. Experimental results demonstrate that the system achieves strong performance in service request handling, memory-augmented dialogue, routing accuracy, and response latency, thereby validating that SLM-driven CEAA effectively supports cognitive persistence and efficient interaction for virtual agents operating at the edge.
0 citationsRead paper
CEAA: A Cognitive Embodied Agents Architecture for Interactive Computing Systems
Current intelligent virtual agents struggle to simultaneously support high-level cognitive reasoning and real-time embodied execution, limiting their deployment in interactive virtual environments. This work proposes a modular cognitive architecture that, for the first time, deeply integrates the Belief-Desire-Intention (BDI) model with the Sense-Think-Act paradigm to create a scalable, adaptive, and interpretable “brain” template. Through a modular design, the architecture unifies cognitive reasoning and behavioral control within a general-purpose 3D interaction platform, enabling the realization of cognitively embodied agents capable of real-time responsiveness, autonomous decision-making, and behavior explanation. The approach effectively bridges the gap between theoretical models and practical deployment, demonstrating both feasibility and broad applicability.
0 citationsRead paper
Cluster-Specific Localized Drift Detection for Efficient Batch Model Adaptation under Controlled Distribution Shift
This work addresses the limitation of existing static tabular datasets, which lack temporal structure and thus hinder the evaluation of model adaptability under controlled distribution shifts. To overcome this, the authors propose a clustering-based framework that transforms static data into controllable, evolving data streams through cluster-based partitioning and structured perturbations. Integrating the ADWIN drift detector with a sliding-window retraining mechanism, the framework systematically evaluates adaptation strategies across six model families, including tree ensembles and online learners. Experiments on five benchmark datasets for classification and regression demonstrate that the proposed methods—particularly Clustered Local ADWIN—accurately model and efficiently respond to localized drifts in feature space, significantly outperforming baseline approaches.
0 citationsRead paper
Recent publications
Latest Papers
Ready for What? Rethinking AI and Robotics Preparedness for Adoption and Policy
研究通过分析982名参与者对17个AI和机器人挑战的评估，揭示了复杂性与准备度之间的关系，强调了在政策制定中应考虑具体挑战的差异。
0 citationsRead paper
Enhancing Virtual Agents through SLMs and Edge-Computing: An Exploratory Evaluation of Think and Memory Processes
This work addresses the pressing need for embodied intelligent agents in complex virtual and metaverse environments to exhibit persistent, adaptive, and context-aware cognitive capabilities. To this end, the authors propose a lightweight edge implementation of a Cognitive Embodied Agent Architecture (CEAA), which, for the first time, integrates small language models (SLMs)—specifically the Qwen2.5 series—onto an NVIDIA Jetson Orin NX platform to form a compact cognitive “brain” endowed with perception, memory, reasoning, and action faculties. Experimental results demonstrate that the system achieves strong performance in service request handling, memory-augmented dialogue, routing accuracy, and response latency, thereby validating that SLM-driven CEAA effectively supports cognitive persistence and efficient interaction for virtual agents operating at the edge.
0 citationsRead paper
CEAA: A Cognitive Embodied Agents Architecture for Interactive Computing Systems
Current intelligent virtual agents struggle to simultaneously support high-level cognitive reasoning and real-time embodied execution, limiting their deployment in interactive virtual environments. This work proposes a modular cognitive architecture that, for the first time, deeply integrates the Belief-Desire-Intention (BDI) model with the Sense-Think-Act paradigm to create a scalable, adaptive, and interpretable “brain” template. Through a modular design, the architecture unifies cognitive reasoning and behavioral control within a general-purpose 3D interaction platform, enabling the realization of cognitively embodied agents capable of real-time responsiveness, autonomous decision-making, and behavior explanation. The approach effectively bridges the gap between theoretical models and practical deployment, demonstrating both feasibility and broad applicability.
0 citationsRead paper
Cluster-Specific Localized Drift Detection for Efficient Batch Model Adaptation under Controlled Distribution Shift
This work addresses the limitation of existing static tabular datasets, which lack temporal structure and thus hinder the evaluation of model adaptability under controlled distribution shifts. To overcome this, the authors propose a clustering-based framework that transforms static data into controllable, evolving data streams through cluster-based partitioning and structured perturbations. Integrating the ADWIN drift detector with a sliding-window retraining mechanism, the framework systematically evaluates adaptation strategies across six model families, including tree ensembles and online learners. Experiments on five benchmark datasets for classification and regression demonstrate that the proposed methods—particularly Clustered Local ADWIN—accurately model and efficiently respond to localized drifts in feature space, significantly outperforming baseline approaches.
0 citationsRead paper