Graph-Based Pseudo-multimodal Contrastive Learning for 12-Lead ECG Representations
为解决12导联ECG分析中难以捕捉导联间依赖性和全局波形模式的问题，提出了一种基于图的伪多模态对比学习框架Graph-CMMC。
0 citationsRead paper
Selected work
Representative Papers
Barycentric Fused Gromov-Wasserstein Balancing for Causal Inference under Multiple Treatments
本文提出CIHSI-Net框架，采用BFG-WB方法解决多治疗条件下因果推断中的估计方差问题，同时保持局部邻近结构，降低计算复杂度。
0 citationsRead paper
SIFT-VTON: Geometric Correspondence Supervision on Cross-Attention for Virtual Try-On
This work addresses the challenge of preserving fine-grained details—such as text and patterns—on garments in diffusion-based virtual try-on, a task hindered by existing methods’ reliance on implicit spatial correspondence learning. To achieve precise geometric alignment, the authors propose the first integration of the classical SIFT feature matching algorithm into this domain. By extracting keypoints to generate explicit geometric guidance and incorporating domain-specific filtering, they derive spatial probability distributions that supervise cross-attention layers within the diffusion model. Evaluated on the VITON-HD dataset, the method significantly improves unpaired evaluation metrics while maintaining strong performance in paired reconstruction, demonstrably enhancing text legibility and pattern fidelity.
0 citationsRead paper
Permanent Data Encoding (PDE): A Visual Language for Semantic Compression and Knowledge Preservation in 3-Character Units
To address challenges in long-term knowledge preservation—namely, overreliance on digital systems, offline inaccessibility, and intergenerational unintelligibility—this paper proposes a non-electric, human-readable visual language framework. The method employs 2–3-character glyphs as atomic semantic units, integrated with a public dictionary protocol and rule-based semantic expansion, enabling high-density semantic compression and transparent, self-contained visual parsing. Its core contribution lies in unifying lightweight encoding with logically derivable syntax, thereby supporting persistent, maintenance-free storage, manual decoding, and logical reconstruction without power. Experimental evaluation demonstrates robustness and interpretability in disaster recovery and human-AI collaborative scenarios. The framework establishes a deployable, zero-maintenance semantic substrate for intergenerational knowledge infrastructure.
0 citationsRead paper
Role-Playing LLM-Based Multi-Agent Support Framework for Detecting and Addressing Family Communication Bias
This study addresses emotional suppression in children stemming from implicit “ideal-parent bias” in familial communication—where parents’ unconscious value-laden discourse inhibits children’s affective expression and autonomy. We propose the first large language model (LLM)-based multi-agent role-playing intervention framework. Leveraging a curated corpus of 30 authentic Japanese parent–child dialogues, we design specialized agents capable of detecting suppressed emotions, identifying implicit biases, and performing contextual inference; a meta-agent integrates domain expertise to generate structured feedback reports. Our framework introduces the first joint quantitative annotation scheme for ideal-parent bias and emotional suppression and delivers actionable recommendations via a four-step empathic discussion protocol. Experimental evaluation shows moderate accuracy in suppressed-emotion classification, high ratings for empathy and practicality of generated feedback, and significant improvements in affective expression and mutual understanding in simulated dialogues.
0 citationsRead paper
Recent publications
Latest Papers
Graph-Based Pseudo-multimodal Contrastive Learning for 12-Lead ECG Representations
为解决12导联ECG分析中难以捕捉导联间依赖性和全局波形模式的问题，提出了一种基于图的伪多模态对比学习框架Graph-CMMC。
0 citationsRead paper
Barycentric Fused Gromov-Wasserstein Balancing for Causal Inference under Multiple Treatments
本文提出CIHSI-Net框架，采用BFG-WB方法解决多治疗条件下因果推断中的估计方差问题，同时保持局部邻近结构，降低计算复杂度。
0 citationsRead paper
SIFT-VTON: Geometric Correspondence Supervision on Cross-Attention for Virtual Try-On
This work addresses the challenge of preserving fine-grained details—such as text and patterns—on garments in diffusion-based virtual try-on, a task hindered by existing methods’ reliance on implicit spatial correspondence learning. To achieve precise geometric alignment, the authors propose the first integration of the classical SIFT feature matching algorithm into this domain. By extracting keypoints to generate explicit geometric guidance and incorporating domain-specific filtering, they derive spatial probability distributions that supervise cross-attention layers within the diffusion model. Evaluated on the VITON-HD dataset, the method significantly improves unpaired evaluation metrics while maintaining strong performance in paired reconstruction, demonstrably enhancing text legibility and pattern fidelity.
0 citationsRead paper
Permanent Data Encoding (PDE): A Visual Language for Semantic Compression and Knowledge Preservation in 3-Character Units
To address challenges in long-term knowledge preservation—namely, overreliance on digital systems, offline inaccessibility, and intergenerational unintelligibility—this paper proposes a non-electric, human-readable visual language framework. The method employs 2–3-character glyphs as atomic semantic units, integrated with a public dictionary protocol and rule-based semantic expansion, enabling high-density semantic compression and transparent, self-contained visual parsing. Its core contribution lies in unifying lightweight encoding with logically derivable syntax, thereby supporting persistent, maintenance-free storage, manual decoding, and logical reconstruction without power. Experimental evaluation demonstrates robustness and interpretability in disaster recovery and human-AI collaborative scenarios. The framework establishes a deployable, zero-maintenance semantic substrate for intergenerational knowledge infrastructure.
0 citationsRead paper
Role-Playing LLM-Based Multi-Agent Support Framework for Detecting and Addressing Family Communication Bias
This study addresses emotional suppression in children stemming from implicit “ideal-parent bias” in familial communication—where parents’ unconscious value-laden discourse inhibits children’s affective expression and autonomy. We propose the first large language model (LLM)-based multi-agent role-playing intervention framework. Leveraging a curated corpus of 30 authentic Japanese parent–child dialogues, we design specialized agents capable of detecting suppressed emotions, identifying implicit biases, and performing contextual inference; a meta-agent integrates domain expertise to generate structured feedback reports. Our framework introduces the first joint quantitative annotation scheme for ideal-parent bias and emotional suppression and delivers actionable recommendations via a four-step empathic discussion protocol. Experimental evaluation shows moderate accuracy in suppressed-emotion classification, high ratings for empathy and practicality of generated feedback, and significant improvements in affective expression and mutual understanding in simulated dialogues.
0 citationsRead paper