个人简介：赵佳宝，副教授，研究生导师。2021年于华东师范大学获得计算机应用技术学科博士学位。曾就职于华东师范大学上海智能教育研究院，2024年进入东华大学信息与智能科学学院计算机应用系，从事教学科研工作。主持国家自然科学基金青年项目，上海市科委项目、CCF-百度松果等项目，发表论文二十余篇，相关研究成果已成功应用在医疗、教育等领域。获得2024上海市计算机学会教学成果奖一等奖。
主要研究方向：（1）小样本持续学习，让机器像人一样能通过少量样例持续学习新知识，助力算法在动态开放环境下的落地与应用。（2）大模型多智能体系统的建模与仿真，研制可持续进化的智能体系统用于医学与教育学的科学发现。
讲授课程：数据结构、计算机网络
邮箱：jbzhao@dhu.edu.cn
办公室：1号学院楼245室
科研项目：
[1] 小样本场景下开放学习者模型构建与应用研究，国家自然科学基金青年项目，30万，2023-01至2025-12，主持
[2] 动态开放环境下的多模态鲁棒决策系统关键技术及原型验证，上海市科技创新行动计划人工智能科技专项，100万，2022-08至2024-08主持
[3] 基于应用场景的大语言模型评测技术研究，CCF-百度松果基金科研项目，20万，2023-06至2024-06，主持
[4] 基于虚拟患者多尺度动态推演的科教平台研究，中央高校自由探索基金项目，10万，2024至2025，主持
[5] 不确定性感知的多模态阿兹海默症早筛技术研究，苏州市多模态数据融合与智慧康养重点实验室2025年开放课题，3万，2025年至2026年，主持
[6] 基于多智能体仿真沙盒的人机协同教学技术研究，国家自然科学基金面上项目，2025-01-01 至 2028-12-31，参与（2/5）
[7] 模型和知识驱动的高效医学图像增强理论与方法，科技创新2030 "新一代人工智能" 重大项目（青年科学家项目），2023-01 至 2025-12，参与（2/24）
代表性学术论文：
[1]Shangheng Du, Jiabao Zhao*, Jinxin Shi, Zhentao Xie, Xin Jiang, Yanhong Bai, and Liang He. A Survey on the Optimization of Large Language Model-based Agents. ACM Comput. Surv.（通讯），2026, SCI一区
[2]Jinxin Shi,Jiabao Zhao*, Xingjiao Wu, Ruyi Xu, Yuan-Hao Jiang, Liang He: Mitigating reasoning hallucination through Multi-agent Collaborative Filtering. Expert Syst. Appl. 263: 125723（通讯）,2025, SCI一区
[3]Jinxin Shi, Jiabao Zhao*, Yifan Yang, Xingjiao Wu, Liang He :Lark: Low-Rank Updates After Knowledge Localization for Few-shot Class-Incremental Learning. ICCV (通讯)，2025, CCF-A
[4]Zhentao Xie, Chengcheng Han, Jinxin Shi, Wenjun Cui, Xin Zhao, Xingjiao Wu,Jiabao Zhao*: RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation. ACL findings（通讯）, 2025, CCF-A
[5]Jiabao Zhao, Yifan Yang, Xin Lin, Jing Yang, Liang He: Looking Wider for Better Adaptive Representation in Few-Shot Learning. AAAI 2021，CCFA
[6]Jie Zhou, Jiabao Zhao, Jimmy Xiangji Huang, Qinmin Vivian Hu, Liang He:MASAD: A large-scale dataset for multimodal aspect-based sentiment analysis. Neurocomputing 455: 47-58 (2021)，SCI二区，共一
[7]Zhentao Xie, Jiabao Zhao*, Yilei Wang, Jinxin Shi, Yanhong Bai, Xingjiao Wu, Liang He: MindScope: Exploring Cognitive Biases in Large Language Models Through Multi-Agent Systems. ECAI 2024: 3308-3315（通讯），CCF-B
[8]Yanhong Bai, Jiabao Zhao*, Tingjiang Wei, Qing Cai, Liang He: A survey of explainable knowledge tracing. Appl. Intell. 54(8): 6483-6514 (2024)（通讯），SCI二区
[9]Yanhong Bai, Jiabao Zhao*, Tingjiang Wei, Jinxin Shi and Liang He: Dynamically Causal-Enhanced Exercise Representations for Adaptive Knowledge Tracing. ICASSP 2025（通讯），CCF-B
[10]Jiancai Zhu,Jiabao Zhao*, Jiayi Zhou, Liang He, Jing Yang, Zhi Zhang: Uncertainty-Aware Few-Shot Class-Incremental Learning. ICASSP 2023: 1-5（通讯），CCF-B
[11]Zhihang Wei, Jing Yang, Jiabao Zhao*: VIP-FSCIL: A More Robust Approach for FSCIL. ICME 2024（通讯），CCF-B
[12]Weijie Li, Luwei Xiao, Xingjiao Wu, Tianlong Ma, Jiabao Zhao, Liang He:Artistry in Pixels: FVS - A Framework for Evaluating Visual Elegance and Sentiment Resonance in Generated Images. ICME 2024: 1-6（通讯），CCF-B
[13]Yilei Wang,Jiabao Zhao*, Deniz S. Ones, Liang He & Xin Xu . Evaluating the ability of large language models to emulate personality[J]. Scientific Reports, 2025,（通讯）,SCI三区
[14]Jiabao Zhao, Xin Lin, Yifan Yang, Jing Yang, Liang He: Cross-Modal Knowledge Distillation For Fine-Grained One-Shot Classification. ICASSP 2021: 4295-4299，CCF-B
[15]Jiabao Zhao, Xin Lin, Jie Zhou, Jing Yang, Liang He, Zhaohui Yang:Knowledge-Based Fine-Grained Classification For Few-Shot Learning. ICME 2020: 1-6，CCF-B
[16]Zihao Zhang, Shuwen Yang, Xingjiao Wu, Jiabao Zhao, Qin Chen, Jing Yang, Liang He:ACRA: An adaptive chain retrieval architecture for multi-modal knowledge-Augmented visual question answering. Knowl. Based Syst. 334: 115136 (2026)，SCI一区
[17]Jiyun Li, Meiqing Zhu, Chen Qian, Jiabao Zhao, Ying Shen: Multimodal Fusion for Alzheimer's Detection from Spontaneous Speech in Label-Scarce Languages. BIBM 2025: 3794-3797，CCF-B
[18]Chen Qian, Yi Chen, Jialong Wang, Jiyun Li, Jiabao Zhao, Ying Liu: DuST-Net: Dual-Stream Temporal Network for Early Alzheimer's Screening from Hierarchical Speech-Language Features. BIBM 2025: 6623-6630，CCF-B
[19]Jiyun Li, Jie Pan, Chen Qian, Ying Shen, Jiabao Zhao: MSA-SAM2Net: A Polyp Segmentation Framework Based on Large Kernel Multi-Scale Attention. ICME 2025，CCF-B
[20]Qin Ni, Tingjiang Wei, Jiabao Zhao, Liang He, Chanjin Zheng: HHSKT: A learner-question interactions based heterogeneous graph neural network model for knowledge tracing. Expert Syst. Appl. 2023，SCI一区