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

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

An Enhanced Iterative Deepening Search Algorithm for the Unrestricted Container Rehandling Problem

Apr 12, 2025

This paper addresses the Unrestricted Container Relocation Problem (UCRP) in container yards—specifically, minimizing the number of relocations under strict time windows and multiple priority classes. To overcome the trade-off between real-time responsiveness and solution completeness inherent in existing exact methods, we propose an iterative deepening search framework integrating an enhanced lower-bound estimation and mutually consistent pruning rules. To our knowledge, this is the first exact approach guaranteeing optimal solutions while meeting stringent runtime constraints for UCRP. Extensive experiments on the CRP-Bench benchmark demonstrate that our algorithm consistently outperforms all state-of-the-art exact solvers across three major UCRP benchmark suites. In same-priority scenarios, it achieves up to a 47% improvement in solving efficiency and significantly reduces response latency.

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

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

An Enhanced Iterative Deepening Search Algorithm for the Unrestricted Container Rehandling Problem

Apr 12, 2025

This paper addresses the Unrestricted Container Relocation Problem (UCRP) in container yards—specifically, minimizing the number of relocations under strict time windows and multiple priority classes. To overcome the trade-off between real-time responsiveness and solution completeness inherent in existing exact methods, we propose an iterative deepening search framework integrating an enhanced lower-bound estimation and mutually consistent pruning rules. To our knowledge, this is the first exact approach guaranteeing optimal solutions while meeting stringent runtime constraints for UCRP. Extensive experiments on the CRP-Bench benchmark demonstrate that our algorithm consistently outperforms all state-of-the-art exact solvers across three major UCRP benchmark suites. In same-priority scenarios, it achieves up to a 47% improvement in solving efficiency and significantly reduces response latency.

0 citationsRead paper