科学研究

Song, S., Ding, K., Zhao, S., Li, S., Li, X., Wang, C., Wan, Q.*, Ji, B., & Yu, J. (2026). Leveraging image as compressed visual prompt and hierarchical visual knowledge for effective image utilization in MLLMs. Proceedings of the AAAI Conference on Artificial Intelligence, 40(30), 25554-25562.

Zhang, Z.⁺, Wan, Q.⁺, Zhao, S., Hao, M., Chen, S., & Wei, L. (2026). Continual relation extraction model based on memory sample selection and historical feature refinement. Applied Soft Computing, 189, 114485.

Wan, Q., Shi, W., Feng, J., Liu, S., Wei, L., Dai, Z., & Sun, J. (2026). Empowering math problem generation and reasoning for large language model via synthetic data based continual learning framework. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing.

Sun, J., Shi, W., Shen, X., Liu, S., Wei, L., & Wan, Q.* (2025). Multi-objective math problem generation using large language model through an adaptive multi-level retrieval augmentation framework. Information Fusion, 119, 103037.

Wei, L., Cui, Y., Chen, M., Wan, Q.*, & Xing, L. (2025). Multi-objective neural policy approach for agile earth satellite scheduling problem considering image quality. Swarm and Evolutionary Computation, 94, 101857.

Liu, S., Feng, J., Shen, X., Liu, S., Wan, Q.*, & Sun, J. (2025, April). VCR: A “Cone of Experience” Driven Synthetic Data Generation Framework for Mathematical Reasoning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 23, pp. 24650-24658).

孙建文, 冯锦天, 万仟*. (2025). 多智能体驱动的虚拟学生模拟助力教师答疑能力提升. 华中师范大学学报（自然科学版）, 59(5), 721-729.

Liu, S., Feng, J., Yang, Z., Luo, Y., Wan, Q.*, Shen, X., & Sun, J. (2024). COMET: “Cone of Experience” enhanced large multimodal model for mathematical problem generation. Science China Information Sciences, 67(12), 220108.

Wan, Q., Wei, L., Zhao, S., & Liu, J. (2023). A span-based multi-modal attention network for joint entity-relation extraction. Knowledge-Based Systems, 262, 110228.

Wan, Q., Du, S., Liu, Y., Fang, J., Wei, L., & Liu, S. (2023). Document-level relation extraction with hierarchical dependency tree and bridge path. Knowledge-Based Systems, 278, 110873.

Wan, Q., Wei, L., Chen, X., & Liu, J. (2021). A region-based hypergraph network for joint entity-relation extraction. Knowledge-Based Systems, 228, 107298.

刘三女牙, 冯锦天, 万仟, 丁可人, 孙建文. (2026). AgentClass: 基于智能体的长周期多尺度课堂仿真建模. 自动化学报(已录用).

Yu, C., Huang, Q., Shen, X., Wan, Q., Dai, Z., Sun, J., & Liang, R. (2026). Towards fine-grained evaluation of explainable recommendation: Aspect-level sentiment consistency for faithfulness assessment. Expert Systems with Applications, 134100.

Yu, C., Huang, Q., Shen, X., Wan, Q., Dai, Z., Sun, J., & Liang, R. (2026). FASC: A feature aspect-level sentiment consistency framework for explainable recommendation evaluation. In Proceedings of the ACM Conference on Recommender Systems.

Zhao, S., Yang, Z., Yan, T., Gong, Y., Wan, Q., Chen, S., Song, S., Wang, C., & Wang, M. (2026). Seeing the Abstract: A benchmark for visual-only metaphor understanding in multimodal large language models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

Xu, W., Zhao, S., Chen, H., Yan, T., Wang, C., Chen, S., & Wan, Q. (2026). Beyond drift: Stabilizing subjective LLM evaluation with information-theoretic rubrics. In Proceedings of the 43rd International Conference on Machine Learning.

Song, S., Li, S., Zhao, S., Li, X., Wan, Q., Wang, C., Yan, T., Jun, M., & Yu, J. (2026). Where does vision meet language? Understanding and refining visual fusion in MLLMs via contrastive attention. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 10051-10060).

Liu, S., Li, J., Wan, Q., He, B., Huang, Z., & Li, Q. (2026). Code-driven programming prediction enhanced by LLM with a feature fusion approach. Information Fusion, 131, 104165.

Chen, S., Li, Q., Wang, Y., & Wan, Q. (2026). Discovering individual differences in the near transfer of cognitive training by learning curve analysis of naturally occurring data. Acta Psychologica, 263, 106279.

Bai, Y., Ma, W., Zhao, S., Yan, T., Song, S., Wang, C., & Wan, Q. (2026). RICA: Re-ranking with intra-modal and cross-modal alignment for text-based person search. Expert Systems with Applications, 306, 130931.

Ma, W., Wu, X., Chen, S., Liu, W., Zhao, S., Wan, Q., & Gu, L. (2026). TSGR2: Image-text matching via triple-level scene graph relation reasoning. Applied Soft Computing, 187, 114323.

Shen, X., Yu, F., Wan, Q., Liang, R., & Sun, J. (2025). Multi-level contrastive learning for knowledge tracing. ACM Transactions on Knowledge Discovery from Data, 19(8), 155:1-155:29.

Yu, F., Sun, J., Wan, Q., Chen, M., Shen, X., & Li, Q. (2025). DiffuQKT: A diffusion-based approach for improved question representation in knowledge tracing. In Proceedings of the 33rd ACM International Conference on Multimedia (pp. 9130-9139).

Shen, X., Yu, F., Liu, Y., Liang, R., Wan, Q., Yang, T., Shi, M., & Sun, J. (2025). Enhancing knowledge tracing with question-based contrastive learning. Knowledge-Based Systems, 325, 113899.

Hao, M., Liu, Z., Liu, Y., Wan, Q., Chen, J., Shu, J., Liu, Y., & Mei, L. (2025). Investigating the relationships among peer moderation, cognitive engagement, and learning achievement in online discussion forums. Interactive Learning Environments, 33(1), 901-919.

Chen, M., Chun, J., Xiang, S., Wei, L., Du, Y., Wan, Q., Chen, Y., & Chen, Y. (2024). Learning to solve quadratic unconstrained binary optimization in a classification way. Advances in Neural Information Processing Systems, 37, 114478-114509.

Shen, X., Yu, F., Liu, Y., Liang, R., Wan, Q., Yang, K., & Sun, J. (2024). Revisiting knowledge tracing: A simple and powerful model. In Proceedings of the 32nd ACM International Conference on Multimedia (pp. 263-272).

Zhang, Z., Zhao, S., Zhang, H., Wan, Q., & Liu, J. (2024). Document-level relation extraction with three channels. Knowledge-Based Systems, 284, 111281.

Zhang, Z., Zhang, H., Wan, Q., & Liu, J. (2024). Entity-relation triple extraction based on relation sequence information. Expert Systems with Applications, 238, 121561.

Wei, L., Chen, M., Xing, L., Wan, Q., Song, Y., Chen, Y., & Chen, Y. (2024). Knowledge-transfer based genetic programming algorithm for multi-objective dynamic agile earth observation satellite scheduling problem. Swarm and Evolutionary Computation, 85, 101460.

Sun, J., Yu, F., Wan, Q., Li, Q., Liu, S., & Shen, X. (2024). Interpretable knowledge tracing with multiscale state representation. In Proceedings of the ACM Web Conference 2024 (pp. 3265-3276).

Zhang, Z., Zhang, H., Wan, Q., & Liu, J. (2022). LELNER: A lightweight and effective low-resource named entity recognition model. Knowledge-Based Systems, 251, 109178.

Chen, X., Li, T., Wan, Q., He, X., Gong, C., Pang, Y., & Liu, J. (2022). MGNet: A novel differential mesh generation method based on unsupervised neural networks. Engineering with Computers, 38(5), 4409-4421.

Zhang, Z., Zhang, H., Wan, Q., Jia, X., Zhang, Z., & Liu, J. (2022). Ancient poetry generation with an unsupervised method. Neural Computing and Applications, 34(11), 8525-8538.

陈新海，刘杰，万仟，龚春叶. (2022). 一种改进的基于深度神经网络的偏微分方程求解方法. 计算机工程与科学, 44(11), 1932-1940.

Wei, L., Xing, L., Wan, Q., Song, Y., & Chen, Y. (2021). A multi-objective memetic approach for time-dependent agile earth observation satellite scheduling problem. Computers & Industrial Engineering, 159, 107530.

Chen, X., Gong, C., Wan, Q., Deng, L., Wan, Y., Liu, Y., Chen, B., & Liu, J. (2021). Transfer learning for deep neural network-based partial differential equations solving. Advances in Aerodynamics, 3, 36.

Chen, X., Chen, R., Wan, Q., Xu, R., & Liu, J. (2021). An improved data-free surrogate model for solving partial differential equations using deep neural networks. Scientific Reports, 11, 20053.

国家重点研发计划子课题，基于跨学科知识层次图谱的认知溯因与路径规划（2024YFC3308204），2025.05-2028.04，90万，在研，课题负责人

企事业单位委托项目，学科大模型及多智能体教学服务，2025.05-2028.04，320万，在研，项目骨干

国家自然科学基金重点项目，面向智慧教育的多模态模型构建方法（62437002），2025.01-2029.12，232万，在研，项目骨干

国家自然科学基金青年项目，基于规律引导和提示学习的多目标智能答疑关键技术研究（62307015），2024.01-2026.12，30万，在研，项目负责人

国家自然科学基金重大项目课题，跨媒体教学资源理解与个性化导学方法研究（62293553），2023.01-2027.12，283万，在研，项目骨干

湖北省自然科学基金青年项目，基于知识抽取的教育视频解构与组织方法研究（2023AFB295），2023.07-2025.06，5万，结题，项目负责人

武汉市知识创新专项项目（曙光计划），基于认知-情感-意图时序因果发现的智能答疑策略回复生成研究（2023010201020390），2023.06-2025.06，10万，结题，项目负责人

中国博士后科学基金面上资助，基于学习状态跟踪和策略因果发现的答疑回复可控生成研究（2023M741304），2024.01-2025.12，5万，结题，项目负责人

湖北省博士后创新研究岗位，2023.07-2025.06，6万，结题，项目负责人

教育部司局项目，促进人工智能助力教育变革研究，2024.11-2025.06，10万，结题，项目骨干

湖北省自然科学基金创新群体项目，智能导学机理与关键技术（2023AFA020），2023.07-2026.06，50万，在研，项目骨干

科技创新2030-“新一代人工智能”重大项目，多时空跨尺度认知与情感规律挖掘方法（2022ZD0117103），2023.03-2026.02，200万，结题，项目骨干

中央高校基本科研业务费资助项目，基于字幕信息抽取的教育视频智能分析方法研究（CCNU23XJ003），2023.01-2024.12，10万，结题，项目负责人

面向教师答疑训练的多智能体虚拟学生模拟方法及系统，ZL 2025 1 1337537.1，孙建文、冯锦天、万仟、刘三女牙，2025年09月18日，已授权

基于智能体模拟教学场景的数学推理数据合成方法及系统，ZL 2025 1 0302608.8，孙建文、冯锦天、万仟、刘三女牙，2025年03月14日，已授权

基于多层次经验学习的教育大模型塔式构建方法，ZL 2024 1 1676504.5，刘三女牙、孙建文、万仟、沈筱譞、杨宗凯，2024年11月22日，已授权

基于情境感知与情绪推理的共情对话生成方法，ZL 2023 1 1852964.4，孙建文、刘智、金嫣、万仟、刘三女牙、杨宗凯，2023年12月29日，已授权

基于层次智能体协同的个性化学习路径规划方法，2026104488587，万仟、谢昊天、孙建文、刘盛英杰、刘三女牙，2026年04月07日，受理中

一种面向软件操作的图文教程自动生成方法及系统，2026104005609，孙建文、冯锦天、万仟、刘三女牙，2026年03月30日，受理中

基于多智能体协同的 AI 素养对话式测评数据构建方法，2026103150709，孙建文、冯锦天、万仟、刘三女牙，2026年03月16日，受理中

基于多目标神经策略优化的敏捷地球卫星调度方法，202511960789X，魏罗娜、董韩琪、崔勇强、陈名、周凌云、万仟，2025年12月24日，受理中

基于多智能体协同的对话式课堂教学质量评估方法及系统，2025112424525，刘三女牙、万仟、孙建文、沈筱譞、陈增照、李卿、舒江波、严中华、王胜明，2025年09月02日，受理中

一种基于大模型的数学试题生成求解协同增强方法及系统，2025108093977，万仟、石旺梓、孙建文、刘三女牙，2025年06月17日，受理中

一种基于自适应多级检索增强的数学题生成方法及系统，2025104076332，孙建文、石旺梓、万仟、刘三女牙，2025年04月02日，受理中

一种面向非结构化序列文本中实体的关系抽取方法及装置，2023116151903，万仟、魏罗娜、刘三女牙、孙建文、陈名、周东波、赵山，2023年11月29日，受理中

一种实体识别方法、装置、设备及介质，2023106127683，刘杰、万仟、魏罗娜、裴向东、陈新海、张庆阳、王庆林，2023年05月29日，受理中