MZMing Zhang

Ming Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ming Zhang has a total of 296 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    POLAR: Policy Optimization through Larger Reasoners

    by Ye Yuan, Zhiping Xiao, Ming Zhang

  • Open Access

    Interests Burn-down Diffusion Process for Personalized Collaborative Filtering

    by Yifang Qin, Zhaobin Li, Arisa Watanabe, Wei Ju, Zhiping Xiao, Ming Zhang

    Generative methods have gained widespread attention in Collaborative Filtering (CF) tasks for their ability to produce high-quality personalized samples aligned with users’ interests. Among them, diffusion generative models have raised increasing attention in recommendation field. Despite that the pioneering efforts have applied the conventional diffusion process to model diffusive user interests, the incongruity between the Gaussian noise and the subtle nature of user's personalized interaction behavior has led to sub-optimal results. To this end, we introduce a specifically-tailored diffusion scheme for interaction systems, namely the interests burn-down process . The interests burn-down process delineates the decay of user interests towards candidate items, complemented by its reverse burn-up process that yields personalized recommendation for users. The inherent burn-down nature of this process adeptly models the diffusive user interests, aligning seamlessly with the requirements of CF tasks. We present a novel recommendation method StageCF to illustrate the superiority of this newly proposed diffusion process. Experimental results have demonstrated the effectiveness of StageCF against existing generative and diffusion-based baseline methods. Furthermore, comprehensive studies validate the functionality of interests burn-down process, shedding light on its capacity to generate personalized interactions.


  • Open Access

    Cross Mol : cross-modal mask-predict pre-training for 3D molecular data

    by Kangjie Zheng, Junwei Yang, Siyu Long, Wei Ju, Wei-Ying Ma, Hao Zhou, Ming Zhang

    Motivation: Self-supervised pre-training models for molecular data have demonstrated notable results across many downstream tasks. The inherent multimodal properties of molecules have also motivated efforts to capture information from different modalities. However, current multimodal molecular pre-training models usually treat these modalities as equal and independent, despite differences in their information content. Three-dimensional (3D) molecular structures generally contain finer-grained information than the simplified molecular-input line-entry system (SMILES), which primarily captures higher-level semantic information, such as molecular topology. Results: We designed a cross-modal mask-predict pre-training model, CrossMol, to capture semantic associations between modalities with unequal information volumes. The model completes missing 3D structure using higher-level semantic information from another modality, such as SMILES. This allows it to learn cross-modal associations and better understand fine-grained 3D structural information. We also introduce a reweighted distance prediction loss to improve the modelling of short-range structural information. Experiments show that CrossMol achieves large performance gains on multiple downstream molecular tasks, attaining state-of-the-art results. Availability and Implementation: The source code and training data are available at https://github.com/zhengkangjie/crossmol. The code is archived at https://doi.org/10.5281/zenodo.19653204.

  • Open Access

    A multi-agent system for spine MRI report generation from multi-sequence imaging

    by Sheng Wang, Zhiping Xiao, Junwei Yang, Gongbo Sun, Han Zhang, Hanwen Xu, Yi Yao, Zachary Miller, William King Iii, Mohammed Kanani, et al.

    Spinal pathology is a leading cause of pain and disability worldwide. Spine magnetic resonance imaging (MRI) is central to clinical evaluation, yet its interpretation remains complex and time-consuming, requiring integration of information across multiple imaging sequences and anatomical regions. Despite recent advances in automated MRI analysis, effectively combining multi-sequence data while preserving sequence-specific diagnostic information remains an open challenge. Here we present SpineAgent, a multi-agent framework for spine MRI report generation built upon a multi-sequence foundation model trained on routine clinical data from 32,047 patients and 453,683 MRI series, comprising a total of 13,441,191 MRI slices. To accommodate diverse modalities of sequences, we first pre-train two DINOv3-based encoders separately on T1- and T2-weighted sequences. We then introduce a continual training strategy that learns a synthesizer to embed images of other sequences using the T1 and T2 encoders, producing patient-level embedding that integrates various signals across MRI sequences. Using these embeddings, SpineAgent achieves state-of-the-art performance, with mean 10.8% AUROC improvement across 17 spinal condition-prediction tasks compared to the best competing method, and demonstrates strong generalizability under cross-manufacturer and cross-cohort evaluation. Beyond classification, SpineAgent enables pathology localization by identifying findings-relevant slices and segmenting pathological regions. It also supports multimodal image–report retrieval, providing a solid foundation for scalable and explainable MRI report generation. We further integrate these validated capabilities of SpineAgent into 37 specialized agents for condition diagnosis, pathological-region localization, and clinically-similar-cases retrieval. Finally, we incorporate their outputs as structured tokens within a Medical Report Agent trained end-to-end for report generation. Through both automated metrics and expert evaluation by five radiologists, SpineAgent achieves leading performance in spine MRI report generation. Together, SpineAgent introduces a continual training approach for multi-sequence spine MRI understanding. By decomposing report generation into clinically grounded subtasks addressed by specialized agents, the SpineAgent framework enables accurate, interpretable and generalizable spine MRI reporting across diverse imaging sequences and anatomical regions.

  • Open Access

    A Comprehensive Survey of Multimodal Foundation Model Evaluation: A Hierarchical Perspective and Extensive Applications

    by Ye Yuan, Junyu Luo, Guancheng Wan, Jinsheng Huang, Chengwu Liu, Junwei Yang, Yifang Qin, Zhiping Xiao, Qingqing Long, Meng Xiao, et al.

    Multimodal foundation models increasingly support querying, interpreting, and acting on heterogeneous data and knowledge sources, but their evaluation remains fragmented. Existing benchmarks are scattered across modalities, tasks, data sources, metrics, and deployment assumptions, making it difficult to judge whether a model can support reliable decisions in data- and knowledge-intensive settings. This survey reviews multimodal foundation model evaluation from a multi-source information fusion perspective. We organize representative datasets, metrics, and protocols into a hierarchical, three-layer evaluation pathway: fundamental competencies, higher-order intelligence, and real-world applications. The first two layers group capabilities, whereas the third examines how those capabilities are evaluated under deployment and domain constraints rather than asserting a universal difficulty ordering. We use this taxonomy to connect evaluations of perception and alignment with those of multimodal reasoning, offline temporal comprehension, online streaming-input understanding, decision making, and planning. We also examine deployment-oriented assessment in healthcare, biology, industry, and society. We characterize benchmark coverage, reported performance, adoption signals, and evaluation design choices. Across these resources, recurring risks include data contamination, insufficient process evidence, weak robustness testing, and limited domain validation. Based on this synthesis, we provide a reporting checklist for building and interpreting evaluation resources. An accompanying repository tracks new benchmarks and related papers.

  • Open Access

    PROBE: VLM-Guided Discrete Structural Reconfiguration for Customized and Efficient Video Retrieval

    by Yiyang Gu, Kaili Liu, Tao Zhe, Binqi Chen, Jiayue Fan, Junwei Yang, Zequn Liu, Zhiping Xiao, Chong Chen, Xiao Luo, et al.

    Existing self-supervised video hashing methods achieve high efficiency by encoding videos into compact binary representations, but they typically rely on a fixed global similarity geometry that enforces a single notion of similarity across all queries. In many real-world retrieval scenarios, however, the same videos may need to be compared under different semantic criteria, such as action, scene, object, emotion, or intent. This requirement gives rise to criterion-dependent video comparison, which remains largely unexplored in efficient hashing-based retrieval frameworks. To this end, we propose an efficient VLM-guided video retrieval paradigm PROBE that leverages a frozen vision–language model (VLM) to inject rich semantic structure into a reusable hash index. Each video is encoded once into a compact binary representation, while prompts act as discrete operators that select criterion-relevant semantic subspaces within the hash space, inducing discrete structural reconfiguration of similarity geometry and enabling customized video–video comparison via efficient masked distance computation. Guided by prompt-conditioned representations from the vision–language teacher, we introduce criterion-induced subspace regularization that transfers semantic geometry into criterion-conditioned hash subspaces while preserving local relational consistency. We further employ a global unconditional alignment and reconstruction objective to stabilize the full hash space across views and datasets. A single model trained jointly on heterogeneous video datasets consistently outperforms strong video hashing baselines and generalizes effectively to unseen datasets and diverse retrieval criteria, demonstrating that VLM-guided discrete structural reconfiguration is key to efficient, customized, and reusable video retrieval. The source code is available at https://github.com/liamgu06/PROBE.

  • Open Access

    AlphaEval: A Comprehensive and Efficient Evaluation Framework for Formula Alpha Mining

    by Hongjun Ding, Binqi Chen, Jinsheng Huang, Taian Guo, Zhengyang Mao, Guoyi Shao, Lutong Zou, Luchen Liu, Ming Zhang


  • Open Access

    EviRAG: Evidence-Guided Retrieval-Augmented Generation for Medical Vision-Language Models

    by Yiyang Gu, Jiayue Fan, Kaili Liu, Bohan Wu, Binqi Chen, Zequn Liu, Zhiping Xiao, Rong-Cheng Tu, Xiao Luo, Ming Zhang


  • Open Access

    A multi-agent system for spine MRI report generation from multi-sequence imaging

    by Zhiping Xiao, Junwei Yang, Gongbo Sun, Han Zhang, Hanwen Xu, Yi Yao, Zachary D. Miller, William E. King, Mohammed M. Kanani, Jalal B. Andre, et al.

    Spinal pathology is a leading cause of pain and disability worldwide. Spine magnetic resonance imaging (MRI) is central to clinical evaluation, yet its interpretation remains complex and time-consuming, requiring integration of information across multiple imaging sequences and anatomical regions. Despite recent advances in automated MRI analysis, effectively combining multi-sequence data while preserving sequence-specific diagnostic information remains an open challenge. Here we present SpineAgent , a multi-agent framework for spine MRI report generation built upon a multi-sequence foundation model trained on routine clinical data from 32,047 patients and 453,683 MRI series, comprising a total of 13,441,191 MRI slices. To accommodate diverse modalities of sequences, we first pre-train two DINOv3-based encoders separately on T1- and T2-weighted sequences. We then introduce a continual training strategy that learns a synthesizer to embed images of other sequences using the T1 and T2 encoders, producing patient-level embedding that integrates various signals across MRI sequences. Using these embeddings, SpineAgent achieves state-of-the-art performance, with mean 10.8% AUROC improvement across 17 spinal condition-prediction tasks compared to the best competing method, and demonstrates strong generalizability under cross-manufacturer and cross-cohort evaluation. Beyond classification, SpineAgent enables pathology localization by identifying findings-relevant slices and segmenting pathological regions. It also supports multimodal image–report retrieval, providing a solid foundation for scalable and explainable MRI report generation. We further integrate these validated capabilities of SpineAgent into 37 specialized agents for condition diagnosis, pathological-region localization, and clinically-similar-cases retrieval. Finally, we incorporate their outputs as structured tokens within a Medical Report Agent trained end-to-end for report generation. Through both automated metrics and expert evaluation by five radiologists, SpineAgent achieves leading performance in spine MRI report generation. Together, SpineAgent introduces a continual training approach for multi-sequence spine MRI understanding. By decomposing report generation into clinically grounded subtasks addressed by specialized agents, the SpineAgent framework enables accurate, interpretable and generalizable spine MRI reporting across diverse imaging sequences and anatomical regions.

  • Open Access

    KEGOD: Kernel-enhanced Latent Substructure Learning for Graph Out-Of-Distribution Detection

    by Yifan Wang, Haodong Zhang, Zhiping Xiao, Yusheng Zhao, Siyu Yi, Nan Yin, Xinwang Liu, Ming Zhang, Wei Ju

    Out-of-Distribution (OOD) detection, which seeks to identify samples deviating from the In-Distribution (ID) training distribution at test time, is crucial for building robust machine learning systems. While extensive efforts have been made for Euclidean data, OOD detection on graph-structured data remains relatively underexplored. On the one hand, the specific properties of a graph may be attributed to its substructures. On the other hand, acquiring labeled data for graph learning is typically time-consuming and labor-intensive. Toward this end, in this paper, we propose a novel kernel-enhanced graph substructure learning framework termed KEGOD for unsupervised graph OOD detection. Specifically, we introduce a learnable graph generator to construct the augmented graph view that preserves distinguishable structure information. Then, for both the input graph and augmented view, a graph neural network (GNN) branch and a graph kernel (GK) branch are incorporated to explore graph latent patterns. By performing multi-branch concordance learning on the extracted graph patterns, our KEGOD captures complementary ID structural semantics in both implicit and explicit manners, enabling reliable detection of OOD graphs through semantic inconsistency. Finally, we build a self-adaptive training mechanism to automatically control diverse sensitivities of the graph patterns. Experimental results on several public graph datasets reveal the superiority of our KEGOD. Our code is available at~ https://github.com/jamesyifan/KEGOD.