Selected work

Representative Papers

DMMRL: Disentangled Multi-Modal Representation Learning via Variational Autoencoders for Molecular Property Prediction

Mar 22, 2026

This work addresses the limitations of existing molecular property prediction methods, which often produce entangled representations that fail to disentangle structural, chemical, and functional factors and inadequately integrate multimodal information. To overcome these challenges, the authors propose a variational autoencoder-based disentangled representation learning framework that decomposes the molecular latent space into shared (structure-related) and private (modality-specific) subspaces. Orthogonality and alignment regularizations are introduced to enhance disentanglement, while a gated attention mechanism enables effective fusion of graph, sequence, and geometric modalities. Evaluated on seven benchmark datasets, the proposed method significantly outperforms current state-of-the-art models, achieving both improved predictive performance and enhanced interpretability of learned representations.

0 citationsRead paper

A warping function-based control chart for detecting distributional changes in damage-sensitive features for structural condition assessment

Jan 18, 2026

This study addresses the limitations of traditional control charts in effectively detecting complex deformations in the distribution of structural damage–sensitive features and their insufficient robustness to data contamination. To overcome these challenges, a novel nonparametric control chart is proposed that models shape variations of probability density functions as warping functions, enabling unified online monitoring of both location shifts and higher-order distributional deformations within a functional data analysis framework. The method uniquely leverages warping functions to characterize the evolution of distributional morphology, offering simultaneous sensitivity to mean/variance shifts and intricate shape changes while maintaining robustness against outliers. Comprehensive validation through numerical simulations and field measurements from stay cables of a long-span cable-stayed bridge demonstrates significantly superior damage detection performance compared to existing approaches.

0 citationsRead paper

MSCoD: An Enhanced Bayesian Updating Framework with Multi-Scale Information Bottleneck and Cooperative Attention for Structure-Based Drug Design

Sep 24, 2025

Current structure-based drug design (SBDD) methods struggle to capture the multi-scale hierarchical nature and intrinsic asymmetry of protein–ligand interactions. To address this, we propose MSCoD—a novel framework that jointly integrates a Multi-Scale Information Bottleneck (MSIB) with an Asymmetric Multi-Head Collaborative Attention (MHCA) mechanism, enabling cross-scale semantic compression and explicit modeling of asymmetric intermolecular interactions. Furthermore, MSCoD unifies molecular generation quality and binding affinity prediction accuracy via a Bayesian generative paradigm coupled with 3D structural encoding. Extensive experiments demonstrate that MSCoD significantly outperforms state-of-the-art methods across multiple benchmark datasets. Notably, it achieves robust generalization on challenging, clinically relevant targets such as KRAS G12D. All code and data are publicly available.

0 citationsRead paper

MSA2-Net: Utilizing Self-Adaptive Convolution Module to Extract Multi-Scale Information in Medical Image Segmentation

Sep 01, 2025

While nnUNet automatically optimizes training hyperparameters, its fixed internal architecture—particularly static convolutional kernel sizes—limits its capacity to model multi-organ, multi-scale anatomical features. To address this, we propose MSA2-Net: an encoder-decoder framework integrating adaptive convolution modules that dynamically adjust kernel sizes to accommodate organ-scale variations; incorporating CSWin Transformer for long-range dependency modeling; and introducing multi-scale convolutional bridges with optimized skip connections to synergistically enhance global-local feature interaction. Evaluated on Synapse, ACDC, Kvasir, and ISIC2017, MSA2-Net achieves Dice scores of 86.49%, 92.56%, 93.37%, and 92.98%, respectively, demonstrating substantial improvements in generalization and segmentation accuracy. The core contributions are a structural adaptive convolution mechanism and a novel multi-scale Transformer fusion architecture.

0 citationsRead paper

Personalized News Recommendation with Multi-granularity Candidate-aware User Modeling

Apr 19, 2025

Existing news recommendation methods predominantly rely on static user representations derived solely from click behaviors, failing to capture users’ diverse interests and overlooking multi-granularity associations between candidate news and user preferences. To address these limitations, we propose a multi-granularity candidate-aware user modeling framework. Our approach introduces, for the first time, a candidate-driven three-level attention mechanism—operating at the word, entity, and news levels—to jointly model fine-grained, dynamic, and context-sensitive relevance between candidate news and user interests. The architecture integrates a news text encoder with a knowledge-enhanced entity extractor and incorporates a dedicated multi-granularity feature fusion network. Extensive experiments on real-world datasets demonstrate that our method achieves a 1.82% improvement in AUC over state-of-the-art baselines, validating the effectiveness of multi-granularity candidate awareness in enhancing recommendation accuracy.

0 citationsRead paper

Recent publications

Latest Papers

DMMRL: Disentangled Multi-Modal Representation Learning via Variational Autoencoders for Molecular Property Prediction

Mar 22, 2026

This work addresses the limitations of existing molecular property prediction methods, which often produce entangled representations that fail to disentangle structural, chemical, and functional factors and inadequately integrate multimodal information. To overcome these challenges, the authors propose a variational autoencoder-based disentangled representation learning framework that decomposes the molecular latent space into shared (structure-related) and private (modality-specific) subspaces. Orthogonality and alignment regularizations are introduced to enhance disentanglement, while a gated attention mechanism enables effective fusion of graph, sequence, and geometric modalities. Evaluated on seven benchmark datasets, the proposed method significantly outperforms current state-of-the-art models, achieving both improved predictive performance and enhanced interpretability of learned representations.

0 citationsRead paper

A warping function-based control chart for detecting distributional changes in damage-sensitive features for structural condition assessment

Jan 18, 2026

This study addresses the limitations of traditional control charts in effectively detecting complex deformations in the distribution of structural damage–sensitive features and their insufficient robustness to data contamination. To overcome these challenges, a novel nonparametric control chart is proposed that models shape variations of probability density functions as warping functions, enabling unified online monitoring of both location shifts and higher-order distributional deformations within a functional data analysis framework. The method uniquely leverages warping functions to characterize the evolution of distributional morphology, offering simultaneous sensitivity to mean/variance shifts and intricate shape changes while maintaining robustness against outliers. Comprehensive validation through numerical simulations and field measurements from stay cables of a long-span cable-stayed bridge demonstrates significantly superior damage detection performance compared to existing approaches.

0 citationsRead paper

MSCoD: An Enhanced Bayesian Updating Framework with Multi-Scale Information Bottleneck and Cooperative Attention for Structure-Based Drug Design

Sep 24, 2025

Current structure-based drug design (SBDD) methods struggle to capture the multi-scale hierarchical nature and intrinsic asymmetry of protein–ligand interactions. To address this, we propose MSCoD—a novel framework that jointly integrates a Multi-Scale Information Bottleneck (MSIB) with an Asymmetric Multi-Head Collaborative Attention (MHCA) mechanism, enabling cross-scale semantic compression and explicit modeling of asymmetric intermolecular interactions. Furthermore, MSCoD unifies molecular generation quality and binding affinity prediction accuracy via a Bayesian generative paradigm coupled with 3D structural encoding. Extensive experiments demonstrate that MSCoD significantly outperforms state-of-the-art methods across multiple benchmark datasets. Notably, it achieves robust generalization on challenging, clinically relevant targets such as KRAS G12D. All code and data are publicly available.

0 citationsRead paper

MSA2-Net: Utilizing Self-Adaptive Convolution Module to Extract Multi-Scale Information in Medical Image Segmentation

Sep 01, 2025

While nnUNet automatically optimizes training hyperparameters, its fixed internal architecture—particularly static convolutional kernel sizes—limits its capacity to model multi-organ, multi-scale anatomical features. To address this, we propose MSA2-Net: an encoder-decoder framework integrating adaptive convolution modules that dynamically adjust kernel sizes to accommodate organ-scale variations; incorporating CSWin Transformer for long-range dependency modeling; and introducing multi-scale convolutional bridges with optimized skip connections to synergistically enhance global-local feature interaction. Evaluated on Synapse, ACDC, Kvasir, and ISIC2017, MSA2-Net achieves Dice scores of 86.49%, 92.56%, 93.37%, and 92.98%, respectively, demonstrating substantial improvements in generalization and segmentation accuracy. The core contributions are a structural adaptive convolution mechanism and a novel multi-scale Transformer fusion architecture.

0 citationsRead paper

Personalized News Recommendation with Multi-granularity Candidate-aware User Modeling

Apr 19, 2025

Existing news recommendation methods predominantly rely on static user representations derived solely from click behaviors, failing to capture users’ diverse interests and overlooking multi-granularity associations between candidate news and user preferences. To address these limitations, we propose a multi-granularity candidate-aware user modeling framework. Our approach introduces, for the first time, a candidate-driven three-level attention mechanism—operating at the word, entity, and news levels—to jointly model fine-grained, dynamic, and context-sensitive relevance between candidate news and user interests. The architecture integrates a news text encoder with a knowledge-enhanced entity extractor and incorporates a dedicated multi-granularity feature fusion network. Extensive experiments on real-world datasets demonstrate that our method achieves a 1.82% improvement in AUC over state-of-the-art baselines, validating the effectiveness of multi-granularity candidate awareness in enhancing recommendation accuracy.

0 citationsRead paper