MYMingdai Yang

Mingdai Yang

*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


Mingdai Yang has a total of 60 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Alignment in Multimodal Large Language Models: A Survey

    by Yuyao Yang, Jiaxing Zhang, Ling Yue, Linsey Pang, Zhiwei Liu, Zixian Ma, Zheng Zhao, Jialiang Yin, Mingdai Yang, Huayi Yang, et al.

    Multimodal large language models (MLLMs) can generate fluent responses but may overlook relevant evidence or violate task and safety constraints. This survey examines MLLM alignment through two complementary gaps: the Modality Gap, concerning cross-modal correspondence and the use of task-relevant evidence, and the Intent Gap, concerning behavior relative to specified goals, constraints, and human expectations. We organize the literature along six dimensions: architecture, objective functions, data construction, training, evaluation, and applications. Across these dimensions, we link alignment mechanisms and supervision assumptions to the failures they target and the evidence supporting their effectiveness. Our analysis clarifies what interface compatibility, target imitation, preference learning, and verifiable rewards can each demonstrate about alignment, together with the limitations of their underlying supervision. We further summarize evaluation at the representation, task, and behavior levels, emphasizing evidence dependence, constraint compliance, and the distinction between observed improvements and explanations of their underlying mechanisms. Applications in robotics, safety, healthcare, recommendation, and climate decision support reveal three recurring requirements: traceable evidence, valid supervision, and decisions that respect domain constraints. Building on this synthesis, we identify four research directions: evidence-consistent alignment across modalities, verified self-correction and test-time alignment, diagnosis-guided repair, and reliable transfer to underrepresented settings.

  • Open Access

    Personalized Recommendation Tool Learning via Autonomous Language Agents

    by Mingdai Yang, Zhiwei Liu, Weizhi Zhang, Yibo Wang, Hao Peng, Philip Yu

    Although large language models (LLMs) have recently gained traction in recommender systems due to their strong reasoning capabilities and extensive world knowledge, previous LLM-based agents suffer from hallucination and context-length limitations, and thus are not suitable for full-ranking recommendation tasks. To circumvent these limitations through architectural design rather than modifying the LLM itself, we propose an agent-based recommendation framework, memory-based Personalized Recommendation Tool learning via autonomous language Agents (PRTA), in which an LLM acts as a central planner interacting with multiple recommendation models as tools. The LLM-based agent is responsible for high-level reasoning and personalized tool selection, while traditional recommendation models perform full-ranking scoring, leveraging their scalability in modeling behavioral patterns. To support personalized tool selection, we design reflection mechanisms that enable the agent to evaluate and compare tools for each user based on user profiles and candidate ranked lists. Extensive experiments across three public datasets demonstrate the superiority of PRTA over traditional recommendation and LLM-based baselines in improving full-ranking recommendation performance. Our code implementation is available online1.

  • Open Access

    AgentDR: Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agents

    by Mingdai Yang, Nurendra Choudhary, Jiangshu Du, Edward W Huang, Philip Yu, Karthik Subbian, Danai Koutra


  • Open Access

    AGP: Auto-Guided Prompt Refinement for Personalized Reranking in Recommender Systems

    by Chen Wang, Mingdai Yang, Zhiwei Liu, Pan Li, Linsey Pang, Qingsong Wen, Philip Yu

    Reranking plays a critical role in recommendation systems by refining initial predictions to better reflect user preferences. While large language models (LLMs) have shown promise in enhancing reranking through contextual reasoning, they still rely heavily on manually crafted prompts—an approach that is both labor-intensive and difficult to scale. Although prompt optimization has been studied in domains like question answering and news recommendation, its adaptation to general item recommendation remains limited due to the unstructured and inconsistent nature of item metadata. To address these challenges, we propose Auto-Guided Prompt Refinement (AGP), a novel framework that automatically refines user profile generation prompts instead of reranking prompts directly. AGP leverages position-based feedback, which encodes item-level ranking misalignments, and introduces batched training with aggregated feedback to ensure robust and generalizable prompt updates. Experimental results on Amazon Movies & TV, Yelp, and Goodreads demonstrate AGP's effectiveness. With only 100 training users, AGP improves NDCG@10 by 5.61%, 2.46%, and 6.18% when reranking SASRec, and by 9.36%, 7.98%, and 20.68% when reranking LightGCN. These results highlight AGP's potential as a scalable, automated solution for LLM-based personalized reranking. Code: https://github.com/ChenMetanoia/AGP

  • Open Access

    Enhanced Pre-training for Recommendation via Hypergraph Structural Entropy

    by Jingyun Zhang, Hao Peng, Mingdai Yang, Philip S. Yu

    Research on recommender systems plays a crucial role in alleviating information overload amid the current proliferation of data while diminishing user decision-making and transaction costs within intricate environments. The prevailing recommendation models currently rely on graph-based methods, such as GCN, GAT, HGNN, and so on, which are constrained by the sparsity of training data and the underutilization of graph structures. In this work, we present EPRHSE, an E nhanced P re-training framework for R ecommendation based on H ypergraph S tructural E ntropy, which encodes the topology of the recommender system. We begin by designing two forms of pre-training tasks to capture the heterogeneous relationships among users or items. These pre-training tasks build multiple auxiliary task hypergraphs, compensate for the sparse interactions between users and items, and unveil latent information. Secondly, we introduce a new method for optimizing the hypergraph structure entropy. The method involves converting the hyperedge information in the hypergraph to form a high-dimensional encoding tree. Hypergraph structure entropy helps decode the essential structure of the recommendation bipartite graph and enables hierarchical clustering of users or items. Thirdly, we propose a hypergraph pooling training methodology incorporating pooling and unpooling layers into the hypergraph convolutional network to amalgamate high-order information. By transferring advanced community insights to primary users or items, the process of social diffusion is enhanced, consequently refining node embedding quality. Compared with 13 representative recommendation approaches on five real datasets, comprehensive experiments demonstrate the effectiveness and advantages of EPRHSE.


  • Open Access

    PCL: Prompt-based Continual Learning for User Modeling in Recommender Systems

    by Mingdai Yang, Fan Yang, Yanhui Guo, Shaoyuan Xu, Tianchen Zhou, Yetian Chen, Simone Shao, Jia Liu, Yan Gao


  • Open Access

    Training Large Recommendation Models via Graph-Language Tokens Alignment

    by Mingdai Yang, Zhiwei Liu, Liangwei Yang, Xiaolong Liu, Chen Wang, Hao Peng, Philip S. Yu


  • Open Access

    Automating Personalization: Prompt Optimization for Recommendation Reranking

    by Chen Wang, Mingdai Yang, Zhiwei Liu, Pan Li, Linsey Pang, Qingsong Wen, Philip Yu

    Modern recommender systems increasingly leverage large language models (LLMs) for reranking to improve personalization. However, existing approaches face two key limitations: (1) heavy reliance on manually crafted prompts that are difficult to scale, and (2) inadequate handling of unstructured item metadata that complicates preference inference. We present AGP (Auto-Guided Prompt Refinement), a novel framework that automatically optimizes user profile generation prompts for personalized reranking. AGP introduces two key innovations: (1) position-aware feedback mechanisms for precise ranking correction, and (2) batched training with aggregated feedback to enhance generalization.

  • Open Access

    Collaborative Alignment for Recommendation

    by Chen Wang, Liangwei Yang, Zhiwei Liu, Xiaolong Liu, Mingdai Yang, Yueqing Liang, Philip S. Yu

    Traditional recommender systems have primarily relied on identity representations (IDs) to model users and items. Recently, the integration of pre-trained language models (PLMs) has enhanced the capability to capture semantic descriptions of items. However, while PLMs excel in few-shot, zero-shot, and unified modeling scenarios, they often overlook the crucial signals from collaborative filtering (CF), resulting in suboptimal performance when sufficient training data is available. To effectively combine semantic representations with the CF signal and enhance recommender system performance in both warm and cold settings, two major challenges must be addressed: (1) bridging the gap between semantic and collaborative representation spaces, and (2) refining while preserving the integrity of semantic representations. In this paper, we introduce CARec, a novel model that adeptly integrates collaborative filtering signals with semantic representations, ensuring alignment within the semantic space while maintaining essential semantics. We present experimental results from four real-world datasets, which demonstrate significant improvements. By leveraging collaborative alignment, CARec also shows remarkable effectiveness in cold-start scenarios, achieving notable enhancements in recommendation performance. The code is available at https://github.com/ChenMetanoia/CARec **REMOVE 2nd URL**://github.com/ChenMetanoia/CARec.


  • Open Access

    Pre-Training with Transferable Attention for Addressing Market Shifts in Cross-Market Sequential Recommendation

    by Chen Wang, Ziwei Fan, Liangwei Yang, Mingdai Yang, Xiaolong Liu, Zhiwei Liu, Philip Yu

    Cross-market recommendation (CMR) involves selling the same set of items across multiple nations or regions within a transfer learning framework. However, CMR's distinctive characteristics, including limited data sharing due to privacy policies, absence of user overlap, and a shared item set between markets present challenges for traditional recommendation methods. Moreover, CMR experiences market shifts, leading to differences in item popularity and user preferences among different markets. This study focuses on cross-market sequential recommendation (CMSR) and proposes the Cross-market Attention Transferring with Sequential Recommendation (CAT-SR) framework to address these challenges and market shifts. CAT-SR incorporates a pre-training strategy emphasizing item-item correlation, selective self-attention transferring for effective transfer learning, and query and key adapters for market-specific user preferences. Experimental results on real-world cross-market datasets demonstrate the superiority of CAT-SR, and ablation studies validate the benefits of its components across different geographical continents. CAT-SR offers a robust and adaptable solution for cross-market sequential recommendation. The code is available at https://github.com/ChenMetanoia/CATSR-KDD/.