二、科研项目
[1]国家自然科学基金项目,多模态教育认知大模型驱动的个性化学习研究,62507001,2026/01-2028/12,30万,主持
[2]北京市自然科学基金项目,融合多模态人机交互与大语言模型的自适应学习研究,4254091,2025/01-2026/12,20万,主持
[3]人才大数据智能分析与评测工信部重点实验室课题,多模态交互协同大模型赋能的产教融合智慧教育研究,MIITECKT25001,2025/06-2025/12,主持
[4]国家电网公司总部科技项目课题,基于双飞翼垂直起降无人机的高速巡航下光电成像与图像处理技术研究,5500-202322539A-3-2-ZN,2023/10-2025/12,190万,主持
[5]北京市博士后科研项目,多模态融合的学习者认知过程建模研究,2023-ZZ-97,2023/05-2024/11,4万,主持
[6]软件开发环境国家重点实验室课题,面向学生的代码智能修复与编程能力评估方法研究,SKLSDE-2022KF-10,2022/11-2023/10,5万,主持
[7]北京市自然科学基金-顺义联合基金项目,基于粒度对齐和区域蒸馏的跨模态视觉注意力高效提升方法研究,L247034,2024/10-2027/09,50万元,参与
[8]国家重点研发计划项目,智能服务适配理论与关键技术,2018YFB1402800,2019/01-2022/12,2191万,参与
[9]国家重点研发计划项目课题,个性化教育资源融合与推荐关键技术,2018YFB1004502,2018/05-2021/04,356万,参与
[10]国家自然科学基金重点项目,大规模在线协同学习的机理与方法研究,61532004,2017/09-2020/12,334万,参与
三、代表性研究成果
[1]Liang Y, Wu W, Li Y, editors. Artificial Intelligence Technologies for Education: Advancements, Challenges, and Impacts[M], 2025. ISBN: 978-3-7258-5037-2 / 978-3-7258-5038-9.
[1]AIDevOps:智能微服务开发、运维原理与实践[M],机械工业出版社, 2022. ISBN: 9787111708650.
[2]Zhao X, Wang D, Bai S, Wang S, Gao Y,Liang Y, et al. Inversed Pyramid Network with Spatial-adapted and Task-oriented Tuning for few-shot learning[J]. Pattern Recognition, 2025, 164: 111415.
[3]Liang Y, Zhang C, An S, et al. FetchEEG: A hybrid approach combining feature extraction and temporal-channel joint attention for EEG-based emotion classification[J]. Journal of Neural Engineering, 2024, 21(3): 036011.
[4]He D, Li Y, Chen L,Liang Y, et al. A two-stage image enhancement and dynamic feature aggregation framework for gastroscopy image segmentation[J]. Neurocomputing, 2024, 601: 128228.
[5]Peng T,Liang Y*, Wu W, et al. CLGT: A graph transformer for student performance prediction in collaborative learning[C]//The 37th AAAI Conference on Artificial Intelligence. AAAI Press, 2023, 37(13): 15947-15954.
[6]Li Y, Qiu J, Yang R, Zhu T, Sheng H, Gui S;Liang Y*. Intelligent tutoring for large-scale personalized programming learning based on knowledge graph [C]//2023 IEEE Frontiers in Education Conference. IEEE, 2023: 1-5.
[7]Han Y, Wu W,Liang Y, et al. Peer grading eliciting truthfulness based on autograder[J]. IEEE Transactions on Learning Technologies, 2023, 16(3): 353–363.
[8]Liang Y, Peng T, Pu Y, et al. HELP-DKT: An interpretable cognitive model of how students learn programming based on deep knowledge tracing[J]. Scientific Reports, 2022,12(1): 1-11.
[9]Liang Y, Wu W, Wu L, et al. Inferring how novice students learn to code: Integrating automated program repair with cognitive model [C]//Conference on Big Data. Springer, Singapore, 2019: 46-56.
全部论著详见:https://scholar.google.com/citations?user=Ky7Ekn0AAAAJ