Ø 个人简介

袁理，工学博士，华南师范大学人工智能学院预聘研究员（砺儒英才）。2026年6月毕业于华南理工大学软件学院，获软件工程博士学位，师从蔡毅教授。2025年1月至2026年1月，获广东省青年优秀科研人才国际培养计划资助，赴香港理工大学计算机系访问交流，合作导师为李青教授（IEEE Fellow）。主要研究领域包括多模态学习、知识图谱、自然语言处理、情感分析及大语言模型。累计发表学术论文二十余篇，其中以第一作者在IEEE TKDE、TAFFC、TASLP以及AAAI、IJCAI、ACM MM、ACL等国际期刊与顶级会议发表论文十余篇。长期担任TKDE、IJCV、TASLP以及ACL、AAAI等国际期刊与顶级会议的审稿人。

Ø 教育背景

博士：华南理工大学，软件工程，2022.09–2026.06，导师：蔡毅教授

联合培养：香港理工大学，计算机系，2025.01–2026.01，合作导师：李青教授

硕士：云南大学，计算机应用技术，2016.06–2022.12，导师：张学杰教授

本科：天津理工大学，信息管理与信息系统，2015.09–2019.06

Ø 工作经历

2026.07至今，华南师范大学，特聘研究员（砺儒英才）

Ø 研究领域

多模态学习、知识图谱、自然语言处理、情感分析、大语言模型

Ø 科研项目

        [1] 国家重点研发项目《⾯向国创嵌⼊式操作系统基于AI的驱动移植》，2025-2026，参与

        [2] 面向程序性文本的知识图谱构建关键技术研究《国家自然科学基金面上项目》，2025-2028，参与

        [3] 广东省基础与应用基础区域联合基金重点项目《基于多元多模态信息融合的手部运动异常疾病辅助诊断机器人研究》，2023-2026，参与

Ø 代表性论文（*通讯作者）

期刊论文：

        [1] Yuan, Li, Yi Cai*, Bingshan Zhu, Zhenghao Liu, Zikun Deng, Qing Li, and Tao Wang. "Visual Knowledge-Enhanced LLaVA for Fine-Grained Multimodal Named Entity Recognition and Grounding." IEEE Transactions on Audio, Speech and Language Processing 34 (2026): 781-795. ( CCF B; JCR:Q1; IF:5.1)

       [2] Yuan, Li, Yi Cai, Jingyu Xu, Qing Li, and Tao Wang*. “A Fine-Grained Network for Joint Multimodal Entity-Relation Extraction.” IEEE Transactions on Knowledge and Data Engineering 37, no. 1 (2025): 1-14. (CCF A; JCR:Q1; IF:10.4)

       [3] Yuan, Li, Jin Wang*, Liang-Chih Yu, Yi Cai, and Xuejie Zhang. “Pruning Self-Attention with Local and Syntactic Dependencies for Aspect Sentiment Triplet Extraction.” IEEE Transactions on Audio, Speech and Language Processing (2025).( CCF B; JCR:Q1; IF:5.1)

       [4] Huang, Shubin, Yi Cai, Li Yuan(共同一作), and Jiexin Wang*. “A knowledge-enhanced network for joint multimodal entity-relation extraction.” Information Processing & Management 62, no. 3 (2025): 104033.(CCF B; JCR:Q1; IF:6.9) [网页]

       [5] Yuan, Li, Jin Wang*, Liang-Chih Yu*, and Xuejie Zhang. “Encoding syntactic information into transformers for aspect-based sentiment triplet extraction.” IEEE Transactions on Affective Computing, 15, no. 2 (2023): 722-735. (CCF B; JCR:Q1; IF:9.8)

       [6] Yuan, Li, Jin Wang*, Liang-Chih Yu*, and Xuejie Zhang. “Hierarchical template transformer for fine-grained sentiment controllable generation.” Information Processing & Management, 59, no. 5 (2022): 103048. (CCF B; JCR:Q1; IF:6.9)

  会议论文：

       [1] Kenfeng Huang, Yi Cai, Xin Wu, Zikun Deng, LI Yuan*. “SMADE-IE: Sparse Multi-Agent Framework with Evidence-Driven Debate for Zero-Shot Information Extraction”Accepted by the EMNLP 2026 Main. (CAAI A)

       [2] Xudong Shen, li yuan (共同一作), Ye Chen, Xin Wu, Yi Cai, Zhiyong Wu*. “Truth or Sophistry? LoFa: A Benchmark for LLM Robustness Against Logical Fallacies.”Accepted by the ACL 2026 Main. (CCF A)

       [3] Yuan, Li, Qingfei Huang, Bingshan Zhu, Yi Cai*, Qingbao Huang, Changmeng Zheng, Zikun Deng, and Tao Wang. "Hybrid-DMKG: A Hybrid Reasoning Framework over Dynamic Multimodal Knowledge Graphs for Multimodal Multihop QA with Knowledge Editing." In Proceedings of the AAAI 2026, vol. 40, no. 33, pp. 28032-28040. 2026. (CCF A)

       [4] Tianchen Yu, Li Yuan(共同一作), Hailin Huang, Jiexin Wang, Yi Cai*. “Mixture-of-Experts Low-Rank Adaptation for Multilingual Code Summarization." In Proceedings of the ASE 2025, pp. 2248-2260. IEEE, 2025. (CCF A)

       [5] Yuan Li, Yi Cai*, Xudong Shen, Qing Li, Qingbao Huang, Zikun Deng, and Tao Wang. "Collaborative Multi-LoRA Experts with Achievement-based Multi-Tasks Loss for Unified Multimodal Information Extraction."Proceedings of the IJCAI 2025. (CCF A)

       [6] Zhou, Bihan, Haopeng Ren, Li Yuan (共同一作), Yi Cai*, Liuwen Cao, and Zikun Deng. "RuleEdit: Towards Rule-Level Knowledge Generalization to Mitigate Over-Editing in Large Language Models." In Findings of the ACL 2025, pp. 3159-3175. (CCF A)

       [7] Yu, Tianchen, Li Yuan (共同一作), Liannan Lin, and Hongkui He. "A Multiple Representation Transformer with Optimized Abstract Syntax Tree for Efficient Code Clone Detection." In Proceedings of the ICSE 2025, pp. 587-587.  (CCF A)

       [8] Liu, Zhenghao, Li Yuan(共同一作), Jiexin Wang, and Yi Cai*. "CSE-WSS: Code Structure Enhancement Framework with Weighted Semantic Similarity for Changeset-Based Bug Localization." In Proceedings of the SANER 2025, pp. 252-263. (CCF B)

       [9] Yuan, Li, Yi Cai*, and Junsheng Huang. "Few-shot joint multimodal entity-relation extraction via knowledge-enhanced cross-modal prompt model." In Proceedings of the ACM MM 2024, pp. 8701-8710. (CCF A)

       [10] Yuan, Li, Yi Cai*, Haopeng Ren, and Jiexin Wang. "A Logical Pattern Memory Pre-trained Model for Entailment Tree Generation." Proceedings of the COLING 2024, pp. 759-772. (CCF B)

       [11] Yuan, Li, Yi Cai*, Jin Wang, and Qing Li. "Joint multimodal entity-relation extraction based on edge-enhanced graph alignment network and word-pair relation tagging." In Proceedings of the AAAI 2023, pp. 11051-11059.(CCF A)

Ø 荣誉奖项

  [1] 2025年，广东省青年优秀科研人才国际培养计划资助在香港理工进行联合培养

      [2] 2025年，受邀在MLNLP学术Talk作题为《面向知识图谱构建的增量少样本关系抽取技术》的报告；

Ø 学术任职

  中国信息学会青年工作委员会，委员

  审稿人：IEEE TKDE、 IJCV、IEEE TASLP以及ACL、AAAI、IJCAI等国际顶级期刊与会议

Ø 联系方式

         Email: yuanli@scnu.edu.cn

个人主页：https://yuanli95.github.io/

谷歌学术：https://scholar.google.com/citations?user=5VtOcSkAAAAJ&hl=en