沈颖

副教授

联系邮箱： sheny76@mail.sysu.edu.cn

联系地址： 402永利集团东校区南实验楼D栋301-A室

个人主页： https://github.com/SYSU-NLPLab/AIGC

沈颖，402永利集团副教授，博士生导师，广东省消防科学与智能应急技术重点实验室副主任。长期从事人工智能、大语言模型、多模态计算学科探索。在该领域出版教科书1部；以第一作者或通讯作者发表CCF A/中科院一区论文160余篇，其中5篇入选ESI前1%高被引论文，2篇入选ESI前1‰热点论文，3篇获国际会议最佳论文奖，多篇工作获IEEE/ACM Fellow高度评价。授权专利25项，已转化专利1项；授权软件著作权20项；发布团体标准1项。主持或作为课题负责人承担国际、国家、省部级研究项目20余项，包括国自然企业创新发展联合基金(人工智能领域)重点支持项目、新一代人工智能国家科技重大专项、工信部攻关专项、军委科技委项目，成果落地于省消防指挥中心、中海油、有色院、建筑科学研究院等多家重要单位。多次入选年度全球前2%科学家榜单、爱思唯尔中国高被引学者榜。获中国安全生产协会安全科技进步奖、广东省科学技术奖二等奖、广东省安全生产协会应急与安全科技进步奖一等奖、广东省土木建筑学会科学技术奖一等奖、广东省学校优秀教学成果奖（高等教育-本科类）一等奖等荣誉。

 

团队学术气氛浓厚，师生关系融洽，科研产出丰富。已毕业员工去向为阿里通义、腾讯、字节、微软等大厂或重要国企，或公务员，或升学读博（境外/海外名校或留本团队）。

欢迎有志于攻读大语言模型、多模态计算、人工智能、自然语言处理的员工报考硕士、博士、博士后！团队亦大量招收实习生，欢迎来信咨询！

 

一、代表性论文（25篇/160余篇）

  1. Jiao Qirui, Chen Daoyuan, Huang Yilun, Li Yaliang, Shen Ying*. From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information. International Journal of Computer Vision (IJCV), 2026. (通讯作者，SCI JCR一区，中科院二区, 录用年IF:11.6)

  2. Dong Chenhe, Li Yinghui, Gong Haifan, Chen Miaoxin, Li Junxin, Shen Ying*, Yang Min*. A Survey of Natural Language Generation. ACM Computing Surveys. 2022. 55(8), 1-38. (通讯作者，SCI JCR一区，中科院一区, 录用年IF:28.0)(获深圳市优秀科技学术论文奖)(高被引论文)

  3. Yang Min, Junhao Liu, Lei Chen, Zhao Zhou, Chen Xiaojun, Shen Ying*. An Advanced Deep Generative Framework for Link Prediction in Dynamic Networks. IEEE Transactions on Cybernetics (TOC). 2020, 50(12), 4946-4957. (通讯作者，SCI JCR一区，中科院一区, 录用年IF:19.118)

  4. Shen Ying, Ding Ning, Zheng Hai-Tao, Li Yaliang, Yang Min*. Modeling Relation Paths for Knowledge Graph Completion. IEEE Transactions on Knowledge and Data Engineering (TKDE). 2020, 33(11): 3607-3617. (第一作者，SCI JCR一区, 录用年IF: 10.4)(高被引论文、热点论文)

  5. Shen Ying, Yang Min, Li Yaliang, Wang Dong, Zheng Haitao, Chen Daoyuan*. Knowledge-based Reasoning Network for Relation Detection. IEEE Transactions on Neural Networks and Learning Systems (TNNLS). 2021, 34(8). 5051-5063. (第一作者，SCI JCR一区，中科院一区, 录用年IF: 14.255)

  6. Deng Yang, Zhang Wenxuan, Xu Weiwen, Shen Ying*, Lam Wai. Non-factoid Question Answering as Query-focused Summarization with Graph-enhanced Multi-hop Inference. IEEE Transactions on Neural Networks and Learning Systems (TNNLS). 2023, 1-15. (通讯作者，SCI JCR一区，中科院一区, 录用年IF: 14.255)(高被引论文)

  7. Yi Zihao, Jiang Qingxuan, Ma Ruotian, Chen Xingyu, Yang Qu, Wang Mengru, Ye Fanghua, Shen Ying*, Tu Zhaopeng, Li Xiaolong, Bo Liefeng. Too Good to be Bad: On the Failure of LLMs to Role-Play Villains. Association for Computational Linguistics (ACL 2026), July 2-7, 2026, San Diego, CA, USA. (通讯作者，CCF A类会议)

  8. Yi Zihao, Ling Zhenqing, Zeng Delong, Luo Haohao, Xu Zhe, Liu Wei, Luan Jian, Cao Wanxia, Shen Ying*. Attention Basin: Why Contextual Position Matters in Large Language Models. Findings of the Association for Computational Linguistics (ACL 2026), July 2-7, 2026, San Diego, CA, USA. (通讯作者，CCF A类会议)

  9. Jiao Qirui, Jiao Dian, Du Nan, Shen Ying*, Liang Lin. Invocation Refiner: A Plug-and-Play Module for Rectifying LLM Tool Invocations. Findings of the Association for Computational Linguistics (ACL 2026), July 2-7, 2026, San Diego, CA, USA. (通讯作者，CCF A类会议)

  10. Zhou Ting, Chen Daoyuan, Jiao Qirui, Ding Bolin, Li Yaliang, Shen Ying*. HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026), June 3 –7, 2026, Denver, CO, USA. (通讯作者，CCF A类会议)

  11. Zhong Ming, Wang Yuanlei, Zhang Liuzhou, An Ruichuan, Zhang Renrui, Lu Ming, Liang Hao, Shen Ying*, Zhang Wentao. VCU-Bridge: Hierarchical Visual Connotation Understanding via Semantic Bridging. Conference on Computer Vision and Pattern Recognition 2026 (CVPR 2026). Denver Convention Center. Jun 3 – 7, 2026. (共同通讯作者，CCF A类会议)

  12. Ling Zhenqing, Chen Daoyuan, Yao Liuyi, Shen Qianli, Li Yaliang, Shen Ying*. Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data. The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025), Dec 2nd - Dec 7th, 2025, San Diego, USA. (通讯作者，CCF A类会议)

  13. Kuang Jiayi, Huang Haojing, Li Yinghui, Liang Xinnian, Xu Zhikun, Li Yangning, Tan Xiaoyu, Qu Chao, Zhang Meishan, Shen Ying*, Philip S. Yu. Atomic Thinking of LLMs: Decoupling and Exploring Mathematical Reasoning Abilities, The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025). Dec 2nd - Dec 7th, 2025, San Diego, USA. (通讯作者，CCF-A类会议)

  14. Xu Zhe, Chen Daoyuan, Ling Zhenqing, Li Yaliang, Shen Ying*. MindGYM: What Matters in Question Synthesis for Thinking-Centric Fine-Tuning? The Thirty-Ninth Annual Conference on Neural Information Processing Systems Datasets & Benchmarks (NeurIPS 2025), Dec 2nd - Dec 7th, 2025, San Diego, USA. (通讯作者，CCF A类会议)

  15. Luo Haohao, Kuang Jiayi, Liu Wei, Shen Ying*, Luan Jian, Deng Yang. Browsing Like Human: A Multimodal Web Agent with Experiential Fast-and-Slow Thinking. In The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), July 27 – August 1st, 2025, Vienna, Austria. (通讯作者，中国计算机学会推荐A类顶级会议)

  16. Li Yinghui, Huang Haojing, Kuang Jiayi, Li Yangning, Guo Shuyu, Qu Chao, Tan Xiaoyu, Zheng Haitao, Shen Ying*, Philip Yu. Refine Knowledge of Large Language Models via Adaptive Contrastive Learning. The 13th International Conference on Learning Representations (ICLR 2025). Singapore. Apr 24 –28, 2025. (通讯作者)

  17. Jiao Qirui, Chen Daoyuan, Huang Yilun, Ding Bolin, Li Yaliang, Shen Ying*. Img-Diff: Contrastive Data Synthesis for Multimodal Large Language Models. The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025 (CVPR 2025), June 11th - June 15th, 2025, Nashville TN, USA. (通讯作者，CCF A类会议)

  18. Li Yinghui, Kuang Jiayi, Huang Haojing, Xu Zhikun*, Liang Xinnian, Yu Yi, Lu Wenlian, Li Yangning, Tan Xiaoyu*, Qu Chao, Shen Ying*, Zheng Hai-Tao, Philip S. Yu. One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs. International Conference on Machine Learning (ICML 2025). July 13-19, 2025. Vancouver, Canada. (通讯作者，中国计算机学会推荐A类顶级会议)

  19. Luo Haohao, Kuang Jiayi, Liu Wei, Shen Ying*, Luan Jian, Deng Yang. Browsing Like Human: A Multimodal Web Agent with Experiential Fast-and-Slow Thinking. In The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), July 27 – August 1st, 2025, Vienna, Austria. (通讯作者，中国计算机学会推荐A类顶级会议)

  20. Zeng Delong, Xie Yuexiang, Li Yaliang, Shen Ying*. Enhancing Multimodal Retrieval via Complementary Information Extraction and Alignment. In The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), July 27 – August 1st, 2025, Vienna, Austria. (通讯作者，中国计算机学会推荐A类顶级会议)

  21. Kuang Jiayi, Li Yinghui, Wang Chen, Luo Haohao, Jiang Wenhao, Shen Ying*. Express What You See: Can Multimodal LLMs Decode Visual Ciphers with Intuitive Semiosis Comprehension? The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), July 27 – August 1st, 2025, Vienna, Austria. (通讯作者，中国计算机学会推荐A类国际会议长文)

  22. Ling Zhenqing, Chen Daoyuan, Liu Yi, Li Yaliang, Shen Ying*. On the Convergence of Zeroth-Order Federated Tuning for Large Language Models. In the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (ACM KDD 2024), August 25-29, 2024, Barcelona, Spain. (通讯作者，中国计算机学会推荐A类会议)

  23. Luo Haohao, Deng Yang, Shen Ying*, Ng See-Kiong, Chua Tat-Seng. Chain-of-Exemplar: Enhancing Distractor Generation for Multimodal Educational Question Generation. The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), August 11–16, 2024, Bangkok, Thailand. (通讯作者，中国计算机学会推荐A类会议)

  24. Xu Zhe, Chen Daoyuan, Kuang Jiayi, Yi Zihao, Li Yaliang, Shen Ying*. Dynamic Demonstration Retrieval and Cognitive Understanding for Emotional Support Conversation. The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2024), Washington D.C., USA. July 14-18, 2024, pp.774-784. (通讯作者，中国计算机学会推荐A类会议)

  25. Li Yinghui, Xu Zishan, Chen Shaoshen, Huang Haojing, Li Yangning, Ma Shirong, Jiang Yong, Li Zhongli, Zhou Qingyu, Zheng Hai-Tao*, Shen Ying*. Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characters. The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), August 11–16, 2024, Bangkok, Thailand. (共同通讯，中国计算机学会推荐A类会议)

 

二、在研项目

  1. 国家自然科学基金企业创新发展联合基金(人工智能领域)重点支持项目，面向网信场景的通用智能体系统自主学习及普适评估研究

  2. 极端暴雨引发的复合型灾害应急救援关键技术与装备研发及示范应用，广东省重点领域研发计划自然灾害防治专项

  3. 新一代人工智能国家科技重大专项，具有环境任务泛化能力的通才智能体

  4. 工业和信息化部装备工业一司自然灾害防治技术装备工程化攻关专项项目（智能无人应急救援），大型储罐灭火智能装备系统

  5. 大模型训练数据准备与评估技术合作项目，华为技术有限公司

  6. 402永利集团-小米智能产业技术联合实验室，北京小米移动软件有限公司

  7. 创新成果路径绘制智能模型的研发，中国烟草总公司广东省公司

  8. 基于知识图谱的电梯检验智能辅助决策研究，国家市场监督管理总局重点实验室

  9. 教育部华为产学合作协同育人项目-AI赋能课程建设-自然语言处理（智能基座昇腾系列课程），教育部高教司