Deep Skew-t Mixture Models
该研究针对高维数据中成分分布既重尾又方向不对称的聚类难题，提出了一种基于广义双曲偏斜t正态均值-方差表示的深度偏斜t混合模型(DStMM)，并通过随机/蒙特卡洛EM算法进行估计。
0 citationsRead paper
Selected work
Representative Papers
Balancing Privacy and Compliance in DeFi: A Zero-Knowledge-Based Auditable Cross-Chain Framework
This study addresses the fundamental conflict between privacy preservation and regulatory compliance in decentralized finance (DeFi) cross-chain transactions by proposing a novel auditable cross-chain protocol paradigm. By systematically integrating zero-knowledge proofs, light client verification, and threshold view key mechanisms, the framework enables trustless compliance verification while safeguarding user privacy. This approach effectively satisfies regulatory standards, including those mandated by the Financial Action Task Force (FATF), thereby resolving critical challenges in compliant interoperability. Consequently, this work establishes a new benchmark for synergizing privacy with regulation, offering a secure and practical technical pathway for RegTech and compliant DeFi ecosystems that balances confidentiality with necessary oversight.
0 citationsRead paper
M$^3$Prune: Hierarchical Collaborative Pruning for Efficient Multi-Modal Multi-Agent Retrieval-Augmented Generation
Multimodal multi-agent Retrieval-Augmented Generation (mRAG) systems face significant challenges including high communication overhead, substantial computational costs, and limited scalability. To address these issues, this work proposes M³Prune, a novel framework that achieves the first unified approach to both intra- and cross-modal collaborative pruning. By constructing a hierarchical cooperative communication graph and integrating graph sparsification, modality alignment scoring, and a progressive edge-pruning strategy, M³Prune effectively eliminates redundant communication edges while preserving task performance and substantially reducing computational demands. Experimental results demonstrate that M³Prune outperforms existing single-agent and multi-agent methods on both general and domain-specific mRAG benchmarks, achieving significant reductions in token consumption without compromising accuracy.
0 citationsRead paper
Convex--Concave Quadratic Spectral Filtering for Graph Neural Networks
Existing low-order spectral graph neural networks suffer from insufficient spectral selectivity, while high-order models face challenges in optimization and high computational complexity. This work proposes DCQ-GNN, which introduces explicit convex-concave quadratic curvature into spectral GNN design for the first time. By constructing adaptive convex-concave quadratic filter banks, the method enhances spectral selectivity through complementary curvature while preserving second-order structural information. A node-adaptive gating mechanism further enables structure-aware spectral responses. DCQ-GNN achieves spectral selectivity comparable to high-order models at a lower computational cost, while ensuring optimization stability and robustness. Experiments show that DCQ-GNN achieves the best average ranking across ten datasets—tied for first on heterophilic graphs and second on homophilic graphs—and exhibits significantly less performance degradation under strong structural perturbations compared to existing baselines.
0 citationsRead paper
GeoContra: From Fluent GIS Code to Verifiable Spatial Analysis with Geography-Grounded Repair
Current large language models often generate GIS code that violates spatial rules—such as geographic semantics, topological relationships, coordinate reference systems (CRS), and units—leading to unreliable outputs. This work proposes GeoContra, a novel framework that formalizes geographic constraints into executable geographic contracts and integrates static checking, runtime verification, and semantic validation to establish a geography-aware, closed-loop repair mechanism. By embedding natural language understanding, CRS metadata, spatial predicates, and topological rules directly into the LLM generation pipeline, GeoContra significantly enhances spatial correctness across 7,079 real-world tasks: achieving up to 81.5% accuracy with proprietary models and yielding an average improvement of 26.6% across eleven open-source models.
0 citationsRead paper
Recent publications
Latest Papers
Deep Skew-t Mixture Models
该研究针对高维数据中成分分布既重尾又方向不对称的聚类难题，提出了一种基于广义双曲偏斜t正态均值-方差表示的深度偏斜t混合模型(DStMM)，并通过随机/蒙特卡洛EM算法进行估计。
0 citationsRead paper
Balancing Privacy and Compliance in DeFi: A Zero-Knowledge-Based Auditable Cross-Chain Framework
This study addresses the fundamental conflict between privacy preservation and regulatory compliance in decentralized finance (DeFi) cross-chain transactions by proposing a novel auditable cross-chain protocol paradigm. By systematically integrating zero-knowledge proofs, light client verification, and threshold view key mechanisms, the framework enables trustless compliance verification while safeguarding user privacy. This approach effectively satisfies regulatory standards, including those mandated by the Financial Action Task Force (FATF), thereby resolving critical challenges in compliant interoperability. Consequently, this work establishes a new benchmark for synergizing privacy with regulation, offering a secure and practical technical pathway for RegTech and compliant DeFi ecosystems that balances confidentiality with necessary oversight.
0 citationsRead paper
M$^3$Prune: Hierarchical Collaborative Pruning for Efficient Multi-Modal Multi-Agent Retrieval-Augmented Generation
Multimodal multi-agent Retrieval-Augmented Generation (mRAG) systems face significant challenges including high communication overhead, substantial computational costs, and limited scalability. To address these issues, this work proposes M³Prune, a novel framework that achieves the first unified approach to both intra- and cross-modal collaborative pruning. By constructing a hierarchical cooperative communication graph and integrating graph sparsification, modality alignment scoring, and a progressive edge-pruning strategy, M³Prune effectively eliminates redundant communication edges while preserving task performance and substantially reducing computational demands. Experimental results demonstrate that M³Prune outperforms existing single-agent and multi-agent methods on both general and domain-specific mRAG benchmarks, achieving significant reductions in token consumption without compromising accuracy.
0 citationsRead paper
Convex--Concave Quadratic Spectral Filtering for Graph Neural Networks
Existing low-order spectral graph neural networks suffer from insufficient spectral selectivity, while high-order models face challenges in optimization and high computational complexity. This work proposes DCQ-GNN, which introduces explicit convex-concave quadratic curvature into spectral GNN design for the first time. By constructing adaptive convex-concave quadratic filter banks, the method enhances spectral selectivity through complementary curvature while preserving second-order structural information. A node-adaptive gating mechanism further enables structure-aware spectral responses. DCQ-GNN achieves spectral selectivity comparable to high-order models at a lower computational cost, while ensuring optimization stability and robustness. Experiments show that DCQ-GNN achieves the best average ranking across ten datasets—tied for first on heterophilic graphs and second on homophilic graphs—and exhibits significantly less performance degradation under strong structural perturbations compared to existing baselines.
0 citationsRead paper
GeoContra: From Fluent GIS Code to Verifiable Spatial Analysis with Geography-Grounded Repair
Current large language models often generate GIS code that violates spatial rules—such as geographic semantics, topological relationships, coordinate reference systems (CRS), and units—leading to unreliable outputs. This work proposes GeoContra, a novel framework that formalizes geographic constraints into executable geographic contracts and integrates static checking, runtime verification, and semantic validation to establish a geography-aware, closed-loop repair mechanism. By embedding natural language understanding, CRS metadata, spatial predicates, and topological rules directly into the LLM generation pipeline, GeoContra significantly enhances spatial correctness across 7,079 real-world tasks: achieving up to 81.5% accuracy with proprietary models and yielding an average improvement of 26.6% across eleven open-source models.
0 citationsRead paper