Continual Graph Memory for Adaptive Recommendation under Intent Drift
本文提出CGM-Rec框架,通过持续更新图记忆来解决用户意图漂移下的自适应推荐问题,提高推荐准确性。
本文提出CGM-Rec框架,通过持续更新图记忆来解决用户意图漂移下的自适应推荐问题,提高推荐准确性。
本文提出Athena,通过知识图谱补全方法解决漏洞影响库识别问题,提高准确率。
本文提出DeepHSIC,一种基于深度学习的接收机,用于解决混合下行IM-NOMA传输中的信号检测问题,通过嵌入专用神经网络模块替代复杂的SIC操作,提高检测效率与准确性。
This study addresses the challenge of insufficient explainability in machine learning–based intrusion detection for unmanned aerial vehicle networks, where the black-box nature of models and high-dimensional multimodal data hinder effective operator decision-making under traditional static visualizations. The work proposes the first integration of conversational Explainable AI (XAI) into this domain, implementing an interactive interface powered by a large language model. Through a controlled user study, it investigates how such an approach influences operators’ comprehension, trust, and reliance behaviors during post-hoc auditing. Findings indicate that while conversational XAI is perceived as more useful, it may reduce operators’ self-reliance, thereby increasing the risk of over-reliance. This reveals a critical trade-off between usability and appropriate dependence in XAI interaction design and motivates a design paradigm that balances ease of use with cognitive forcing mechanisms.
Current multimodal large language models for ECG diagnosis suffer from limited interpretability, susceptibility to hallucinations, and deviations from clinical guidelines, undermining their clinical reliability. To address these issues, this work proposes a knowledge-anchored multimodal framework that, for the first time, distills authoritative ECG guidelines into structured explanatory knowledge offline and integrates this as a fixed module within the prompting pipeline. The approach combines CNN-based ECG feature extraction with Grad-CAM to produce class-specific heatmaps and factual evidence packages, guiding the model to generate structured diagnostic reports aligned with clinical standards. Evaluated on the PTB-XL test set, the method improves BERTScore for the impression section from 0.818 to 0.953, significantly enhancing guideline adherence, semantic quality, and interpretability while maintaining strong classification performance.
本文提出CGM-Rec框架,通过持续更新图记忆来解决用户意图漂移下的自适应推荐问题,提高推荐准确性。
本文提出Athena,通过知识图谱补全方法解决漏洞影响库识别问题,提高准确率。
本文提出DeepHSIC,一种基于深度学习的接收机,用于解决混合下行IM-NOMA传输中的信号检测问题,通过嵌入专用神经网络模块替代复杂的SIC操作,提高检测效率与准确性。
This study addresses the challenge of insufficient explainability in machine learning–based intrusion detection for unmanned aerial vehicle networks, where the black-box nature of models and high-dimensional multimodal data hinder effective operator decision-making under traditional static visualizations. The work proposes the first integration of conversational Explainable AI (XAI) into this domain, implementing an interactive interface powered by a large language model. Through a controlled user study, it investigates how such an approach influences operators’ comprehension, trust, and reliance behaviors during post-hoc auditing. Findings indicate that while conversational XAI is perceived as more useful, it may reduce operators’ self-reliance, thereby increasing the risk of over-reliance. This reveals a critical trade-off between usability and appropriate dependence in XAI interaction design and motivates a design paradigm that balances ease of use with cognitive forcing mechanisms.
Current multimodal large language models for ECG diagnosis suffer from limited interpretability, susceptibility to hallucinations, and deviations from clinical guidelines, undermining their clinical reliability. To address these issues, this work proposes a knowledge-anchored multimodal framework that, for the first time, distills authoritative ECG guidelines into structured explanatory knowledge offline and integrates this as a fixed module within the prompting pipeline. The approach combines CNN-based ECG feature extraction with Grad-CAM to produce class-specific heatmaps and factual evidence packages, guiding the model to generate structured diagnostic reports aligned with clinical standards. Evaluated on the PTB-XL test set, the method improves BERTScore for the impression section from 0.818 to 0.953, significantly enhancing guideline adherence, semantic quality, and interpretability while maintaining strong classification performance.