WLWeiming Lu

Weiming Lu

*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


Weiming Lu has a total of 76 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation

    by Siqi Chen, Xinyu Dong, Haolei Xu, Xingyu Wu, Fei Tang, Hang Zhang, Yuchen Yan, Linjuan Wu, Wenqi Zhang, Guiyang Hou, et al.


  • RexUniNLU: Recursive Method With Explicit Schema Instructor for Universal Natural Language Understanding

    by Chengyuan Liu, Shihang Wang, Yangyang Kang, Fubang Zhao, Kun Kuang, Weiming Lu, Changlong Sun, Fei Wu

    Information Extraction (IE) and Text Classification (CLS) serve as the fundamental pillars of NLU, with both disciplines relying on analyzing input sequences to categorize outputs into pre-established schemas. However, there is no existing encoder-based model that can unify IE and CLS tasks from this perspective. To fully explore the foundation shared within NLU tasks, we have proposed a recursive method with explicit schema instructor for universal NLU. Specifically, we first redefine the true universal information extraction (UIE) with a formal formulation that covers almost all extraction schemas, including quadruples and quintuples which remain unsolved for previous UIE models. Then, we expands the formulation to all CLS and multi-modal NLU tasks. Based on that, we introduce RexUniNLU, an universal NLU solution that employs explicit schema constraints for IE and CLS, which encompasses all IE and CLS tasks and prevent incorrect connections between schema and input sequence. To avoid interference between different schemas, we reset the position ids and attention mask matrices. Extensive experiments are conducted on IE, CLS in both English and Chinese, and multi-modality, revealing the effectiveness and superiority.


  • Open Access

    TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence

    by Guiyang Hou, Xing Gao, Yuchuan Wu, Xiang Huang, Wenqi Zhang, Zhe Zheng, Yongliang Shen, Jialu Du, Fei Huang, Yongbin Li, et al.

    Recently, Large Language Models (LLMs) have made significant progress in IQ-related domains that require careful thinking, such as mathematics and coding. However, enhancing LLMs' cognitive development in social domains, particularly from a post-training perspective, remains underexplored. Recognizing that the social world follows a distinct timeline and requires a richer blend of cognitive modes (from intuitive reactions (System 1) and surface-level thinking to deliberate thinking (System 2)) than mathematics, which primarily relies on System 2 cognition (careful, step-by-step reasoning), we introduce Temporal-aware Hierarchical Cognitive Reinforcement Learning (TimeHC-RL) for enhancing LLMs' social intelligence. In our experiments, we systematically explore improving LLMs' social intelligence and validate the effectiveness of the TimeHC-RL method, through five other post-training paradigms and two test-time intervention paradigms on eight datasets with diverse data patterns. Experimental results reveal the superiority of our proposed TimeHC-RL method compared to the widely adopted System 2 RL method. It gives the 7B backbone model wings, enabling it to rival the performance of advanced models like DeepSeek-R1 and OpenAI-O3. Additionally, the systematic exploration from post-training and test-time interventions perspectives to improve LLMs' social intelligence has uncovered several valuable insights.

  • Open Access

    Structural-Temporal Coupling Anomaly Detection with Dynamic Graph Transformer

    by Chang Zong, Yueting Zhuang, Jian Shao, Weiming Lu

    Detecting anomalous edges in dynamic graphs is an important task in many applications over evolving triple-based data, such as social networks, transaction management, and epidemiology. A major challenge with this task is the absence of structural-temporal coupling information, which decreases the ability of the representation to distinguish anomalies from normal instances. Existing methods focus on handling independent structural and temporal features with embedding models, which ignore the deep interaction between these two types of information. In this paper, we propose a structural-temporal coupling anomaly detection architecture with a dynamic graph transformer model. Specifically, we introduce structural and temporal features from two integration levels to provide anomaly-aware graph evolutionary patterns. Then, a dynamic graph transformer enhanced by two-dimensional positional encoding is implemented to capture both discrimination and contextual consistency signals. Extensive experiments on six datasets demonstrate that our method outperforms current state-of-the-art models. Finally, a case study illustrates the strength of our method when applied to a real-world task.

  • Specialized Mathematical Solving by a Step-By-Step Expression Chain Generation

    by Wenqi Zhang, Yongliang Shen, Guiyang Hou, Kuangyi Wang, Weiming Lu

    Math Solving requires both semantic understanding and relation reasoning. Most current approaches treat it as a translation task from natural language to mathematical symbols, generating tokens one by one. However, token-level generation is usually vulnerable when confronted with diverse annotations and complex reasoning. We consider the equation is an ordered combination of multiple sub-expressions, and math reasoning should be performed on the sub-expression level rather than the token level. We treat sub-expression as a minimum generative unit and minimum reasoning node. At each step, candidate sub-expression nodes are generated in parallel, and the whole reasoning chain is deduced by combining multiple nodes in order. Besides, we can obtain multiple valid reasoning chains by sub-expression searching, further improving interpretability and precision. Experiments on multilingual datasets show our method significantly outperforms the baselines. Additionally, our approach is more stable and efficient when faced with the challenges of diverse annotation and complex reasoning with limited resources. Moreover, our approach can be seamlessly integrated with large language models (LLMs), enhancing LLM's mathematical reasoning capabilities at a minimal cost. Experiments show a synergistic collaboration between general-purpose LLM and our specialized model yields superior performance.


  • Graph Neural Networks with Geometric Edge Fusion and Point Downsampling for Drug-Target Interaction Prediction

    by Xinyu Zhu, Li Li, Weiming Lu

    Accurate and efficient prediction of Drug-Target Interactions (DTIs) can potentially accelerate the drug discovery process. We propose a framework, namely GeoPD-DTI, that utilizes Geometric Edge Fusion to effectively integrate distance information from various sources to model drugs and target proteins, and leverages Point Downsampling to reduce the computational burden of modeling protein 3D structures without compromising prediction accuracy. Moreover, to alleviate the ambiguity in substructure modeling of drug 3D molecular graphs, we introduce molecular fingerprints as a supplement to the 3D molecular graphs. Our framework achieves state-of-the-art performance on two benchmark datasets. We also visualize the edge weights learned by our model, which demonstrates clear patterns of interactions. Our code is available at https://github.com/Hienyriux/GeoPD-DTI.

  • Open Access

    MProto: Multi-Prototype Network with Denoised Optimal Transport for Distantly Supervised Named Entity Recognition

    by Shuhui Wu, Yongliang Shen, Zeqi Tan, Wenqi Ren, Jietian Guo, Shiliang Pu, Weiming Lu

    Distantly supervised named entity recognition (DS-NER) aims to locate entity mentions and classify their types with only knowledge bases or gazetteers and unlabeled corpus. However, distant annotations are noisy and degrade the performance of NER models. In this paper, we propose a noise-robust prototype network named MProto for the DS-NER task. Different from previous prototype-based NER methods, MProto represents each entity type with multiple prototypes to characterize the intra-class variance among entity representations. To optimize the classifier, each token should be assigned an appropriate ground-truth prototype and we consider such token-prototype assignment as an optimal transport (OT) problem. Furthermore, to mitigate the noise from incomplete labeling, we propose a novel denoised optimal transport (DOT) algorithm. Specifically, we utilize the assignment result between Other class tokens and all prototypes to distinguish unlabeled entity tokens from true negatives. Experiments on several DS-NER benchmarks demonstrate that our MProto achieves state-of-the-art performance. The source code is now available on Github.

  • Open Access

    ML-LJP: Multi-Law Aware Legal Judgment Prediction

    by Yifei Liu, Yiquan Wu, Yating Zhang, Changlong Sun, Weiming Lu, Fei Wu, Kun Kuang