
基本信息
导师姓名:董彬
性别:男
职称:教授
电子邮件:bindong@bjzgca.edu.cn
任职单位:北京大学博雅特聘教授、北京中关村学院常务副院长
董彬,北京大学博雅特聘教授,任职北京大学北京国际数学研究中心,兼任北京中关村学院常务副院长、北京大学国际机器学习研究中心副主任、北京大学长沙计算与数字经济研究院副院长、国家生物医学成像科学中心研究员。2003年本科毕业于北京大学数学科学学院、2005年在新加坡国立大学数学系获得硕士学位、2009年在美国加州大学洛杉矶分校数学系获得博士学位。博士毕业后曾在美国加州大学圣迭戈分校数学系任访问助理教授、2011-2014年在美国亚利桑那大学数学系任助理教授,2014年底入职北京大学。主要研究领域为机器学习、科学计算和计算成像。现任期刊《SIAM Journal on Scientific Computing》、《SIAM Journal on Imaging Science》、《Inverse Problems and Imaging》、《Communications in Mathematical Sciences》编委、《CSIAM Transactions on Applied Mathematics》、《Journal of Computational Mathematics》、《Journal of Machine Learning》副主编。
人物经历
2024年至今,兼任北京中关村学院常务副院长
2024年至今,北京大学北京国际数学研究中心博雅特聘教授
2023年至今,北京大学北京国际数学研究中心教授
2022年至今,北京大学机器学习研究中心副主任
2019年至2022年,北京大学人工智能研究院人工智能理论中心主任
2018年至2022年,北京大学北京国际数学研究中心长聘副教授
2014年至2018年, 北京大学北京国际数学研究中心副教授
2011年至2014年, 美国亚利桑那大学(University of Arizona)助理教授
2009-07至2011-07, 美国加州大学圣迭戈分校(UCSD)数学系SEW助理教授
2009年, 获得加州大学洛杉矶分校(UCLA)数学专业博士学位
2005年, 获得新加坡国立大学数学专业硕士学位
2003年, 获得北京大学数学专业学士学位
荣誉与奖项
主持“十三五”国家重大科技基础设施“多模态跨尺度生物医学成像设施”装置四:全尺度图像整合系统、科技部国家重点研发计划1项、国家重点研发计划1项、国家自然科学基金重大项目1项、北京市自然科学基金重点项目2项、中组部国家“千人计划”青年项目1项、美国国家科学基金项目1项,参与科技部国家重点研发计划1项、国家自然科学基金重点项目1项、重大研究计划集成项目1项。
2014年获得求是杰出青年学者奖。2015年入选中组部“千人计划”青年项目。2019年入选科技部创新人才推进计划。2020年入选中组部“万人计划”领军人才。2022年受邀在世界数学家大会(ICM)做45分钟报告。2023年入选新基石研究员项目,同年获得王选杰出青年学者奖。2027年受邀在国际工业与应用数学大会(ICIAM)做邀请报告。
主要成就
科研亮点:
在应用和计算数学,尤其是图像处理及数据分析中的数学建模、算法设计和理论分析中做出突出贡献。
在图像处理方面,作为计算机视觉和图像科学的关键领域,广泛应用于生物医学成像、遥感等领域。其中,偏微分方程(PDE)和小波方法作为重要的两类数学工具,已得到深入研究和极为广泛应用,也是整个应用数学领域近30年来最具活力和代表性的研究方向。董彬在这一领域取得了显著的突破,他与合作者一起揭示了PDE和小波方法之间的深层次联系,证明了基于小波变换的优化模型和迭代算法与PDE模型之间存在渐进收敛关系。这一发现不仅确立了小波方法和PDE方法之间的一般性联系,还将微分算子的几何意义和小波框架的稀疏逼近联系起来,提供了全新的几何视角。董彬团队进一步将这些理论成果应用于实际问题中,设计了一系列结合了小波和PDE的优点、兼顾多尺度稀疏逼近和几何直观的新模型,并且成功地在医疗影像分析中得到了应用。
在深度学习方面,董彬团队建立了数值微分方程和深层神经网络架构之间的联系。团队通过常微分方程(ODE)数值格式指导深度学习中的深层神经网络架构设计,并提出了由ODE数值格式诱导的深层网络架构ODE-Net,在大规模图像识别数据集上验证了该方法的有效性。他们还利用离散PDE和卷积网络的结构相似性,提出了一种全新的深层网络架构PDE-Net,该网络能从海量数据中学习出背后未知的PDE模型并进行精确预测。董彬团队将以上研究发展为机理与数据融合的新思路,提出了融合深度学习、强化学习、最优控制和动力系统的计算成像、PDE求解、PDE反问题等新算法,这些算法不仅具备优良的精度、效率和泛化性,还具有良好的可解释性。
在医疗临床应用方面,董彬团队与北京大学肿瘤医院合作,运用机理与数据融合的建模思想,在辅助诊断上构建了包括脏器脂肪勾画软件、食管胃结合部癌临床参数自动计算软件、高精度的胃癌抗肿瘤治疗疗效预后软件和胃癌腹膜转移预测软件等多个人工智能模型,以上成果已北京大学肿瘤医院推广和使用。在此基础上,董彬团队与北京大学肿瘤医院消化科深度合作,构建了能够有效整合临床、影像、病理、检验等多模态数据的人工智能框架,实现了对多时间点、多图像模态、不同尺度医疗数据的处理和分析能力。该框架在面向治疗决策这一临床核心任务上,针对数据体量较小、类型复杂的消化肿瘤,在肿瘤的分型分期、化疗免疫治疗疗效的预测等实际应用上,达到了与高年资医生相近的判断水平。
学术专著:
1. PuYang, Bin Dong, MoColl: Agent-Based Speci c and General Model Collaboration for Image Captioning, arXiv:2501.01834, 2025.
2. Ziju Shen, Haimiao Zhang, Bin Dong, Jun Qiu, Yunxiang Li, Zhili Cui, Incomplete Data Multi-Source Static Computed Tomography Reconstruction with Di usion Priors and Implicit Neural Representation, arXiv:2501.01013, 2025.
3. Yifan Luo, Zhennan Zhou, Meitan Wang, Bin Dong, Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weighting, arXiv:2410.10150, 2024.
4. Zuoyuan Li, Bin Dong, Pingwen Zhang, State-observation augmented di usion model for non linear assimilation, arXiv:2407.21314, 2024.
5. Bin Dong, Ting Lin, Zuowei Shen, Peichu Xie, Analysis of a wavelet frame based two-scale model for enhanced edges, arXiv:2401.02688.
6. Xinyu Xiao, Zhennan Zhou, Bin Dong, Dingjiong Ma, Li Zhou, Jie Sun, Meta-DSP: A Meta Learning Approach for Data-Driven Nonlinear Compensation in High-Speed Optical Fiber Sys tems, arXiv:2311.10416.
7. Zifan Chen, Jiazheng Li, Jie Zhao, Yiting Liu, Hongfeng Li, Bin Dong, Lei Tang and Li Zhang, PropNet: Propagating 2D Annotation to 3D Segmentation for Gastric Tumors on CT Scans, arXiv:2305.17871.
8. Peng Bao, Gong Wang, Ruijie Yang, Bin Dong, Deep Reinforcement Learning for Beam Angle Optimization of Intensity-Modulated Radiation Therapy, arXiv:2303.03812.
学术论文:
2022年至2025年3月发表的论文。
1. Fangxu Zhou, Zehua Li, Haifeng Li, Yao Lu, Linjia Cheng, Ying Zhang, Zichen Wang, Jing Nie, Heping Cheng, Bin Dong, Lei Ma, Li Yang, An Initiative on Digital Nephrology: The Kidney Imageomics Project, doi.org/10.1093/nsr/nwaf034, 2025.
2. Bin Dong, Li Zhang, Jiajia Yuan, Yang Chen, Quanzheng Li, Lin Shen, Large language models: game-changers in the healthcare industry, Science Bulletin, S2095-9273, 2024.
3. Zifan Chen, Yang Chen, Yu Sun, Lei Tang, Li Zhang, Yajie Hu, Meng He, Zhiwei Li, Siyuan Cheng, Jiajia Yuan, Zhenghang Wang, Yakun Wang, Jie Zhao, Jifang Gong, Liying Zhao, Baoshan Cao, Guoxin Li, Xiaotian Zhang, Bin Dong, and Lin Shen, Predicting gastric cancer response to anti-HER2 therapy or anti-HER2 combined immunotherapy based on multi-modal data, Signal Transduction and Targeted Therapy, 9:222, 2024.
4. Qi Sun, Hexin Dong, Zewei Chen, Jiacheng Sun, Zhenguo Li, Bin Dong, Layer-Parallel Training of Residual Networks with Auxiliary-Variable Networks, Numerical Methods for Partial Di erential Equations, 40(6), e23147, 2024 (arXiv:2112.05387).
5. Haocheng Ju, Haimiao Zhang, Lin Li, Xiao Li, Bin Dong, A Comparative Study of Deep Learning and Iterative Algorithms for Joint Channel Estimation and Signal Detection, Signal Processing, 109554, 2024 (arXiv:2303.03678).
6. Pu Yang and Bin Dong, L2SR: Learning to Sample and Reconstruct for Accelerated MRI, Inverse Problems, 40 055015, 2024 (arXiv:2212.02190).
7. Mingze Yuan, Peng Bao, Jiajia Yuan, Yunhao Shen, Zifan Chen, Yi Xie, Jie Zhao, Quanzheng Li, Yang Chen, Li Zhang, Lin Shen, Bin Dong, Large language models illuminate a progressivepathway to arti cial intelligent healthcare assistant, Medicine Plus, 1000302024.
8. Chenxi Xie, Yueyuxiao Yang, Hao Yu, Qiushun He, Mingze Yuan, Bin Dong, Li Zhang, Meng Yang, RNA Velocity Prediction via Neural Ordinary Di erential Equation, iScience, 27(4), 2024.
9. Meng He, Zi-fan Chen, Song Liu, Yang Chen, Huan Zhang, Li Zhang, Jie Zhao, Jie Yang, Xiao-tian Zhang, Lin Shen, Jian-bo Gao, Bin Dong, Lei Tang, Deep learning model based on multi-lesion and time series CT images for predicting the bene ts from anti-HER2 targeted therapy in stage IV gastric cancer, Insights into Imaging, 15(59), 2024.
10. Bin Dong, Xuhua He, Pengfei Jin, Felix Schremmer, Qingchao Yu, Machine learning assisted exploration for a ne Deligne-Lusztig varieties, Peking Mathematical Journal, pp. 150, 2024 (arXiv:2308.11355).
11. Zhuoyuan Li, Bin Dong, Pingwen Zhang, Latent assimilation with implicit neural represen tations for unknown dynamics, Journal of Computational Physics, 506, 112953, 2024 (arXiv:2309.09574).
12. Yifan Luo, Yiming Tang, Chengfeng Shen, Zhennan Zhou, Bin Dong, Prompt engineering through the lens of optimal control, Journal of Machine Learning, 2, 241-258, 2023 (arXiv:2310.14201).
13. Zhengyi Li, Yanli Wang, Hongsheng Liu, Zidong Wang, Bin Dong, Solving Boltzmann equation with neural sparse representation, SIAM Journal on Scienti c Computing, 46(2), C186C215,2023 (arXiv:2302.09233).
14. Jiajia Yuan, Peng Bao, Zifan Chen, Mingze Yuan, Jie Zhao, Jiahua Pan, Yi Xie, Yanshuo Cao, Yakun Wang, Zhenghang Wang, Zhihao Lu, Xiaotian Zhang, Jian Li, Lei Ma, Yang Chen, Li Zhang, Lin Shen and Bin Dong, Advanced Prompting as a Catalyst: Empowering Large Language Models in the Management of Gastrointestinal Cancers, The Innovation Medicine, 1(2), 100019, 2023.
15. Zhanhong Ye, Xiang Huang, Hongsheng Liu, Bin Dong, Meta-Auto-Decoder: A Meta-Learning Based Reduced Order Model for Solving Parametric Partial Di erential Equations, Communications on Applied Mathematics and Computation, 6(2), 1096-1130, 2023 (arXiv:2302.08263).
16. Wei Wan, Yuejin Zhang, Chenglong Bao, Bin Dong, Zuoqiang Shi, A scalable deep learning approach for solving high-dimensional dynamic optimal transport, SIAM Journal on Scienti c Computing, 45(4), B644B563, 2023 (arXiv:2205.07521).
17. Zhiwen Deng, Jing Wang, Hongsheng Liu, Hairun Xie, BoKai Li, Miao Zhang, Tingmeng Jia, Yi Zhang, Zidong Wang, Bin Dong, Prediction of transonic ow over supercritical airfoilsusing geometric-encoding and deep-learning strategies, Physics of Fluids, 35(7), 2023 (arXiv:2303.03695).
18. Meng He, Zi-Fan Chen, Li Zhang, Xiangyu Gao, Xiaoyi Chong, Hao-shen Li, Lin Shen, Jiafu Ji, Xiaotian Zhang, Bin Dong, Zi-Yu Li and Tang Lei, Associations of subcutaneous fat area and Systemic Immune-in ammation Index with survival in patients with advanced gastric cancer receiving dual PD-1 and HER2 blockade, Journal of ImmunoTherapy of Cancer, 11:e007054,2023.
19. Chaoyan Huang, Tingting Wu, Juncheng Li, Bin Dong, Tieyong Zeng, Single-Particle Reconstruction in Cryo-EM based on Three-dimensional Weighted Nuclear Norm Minimization,Pattern Recognition, doi.org/10.1016/j.patcog.2023.109736, 2023.
20. Jiazheng Li, Zifan Chen, Yang Chen, Jie Zhao, Meng He, Xiaoting Li, Li Zhang, Bin Dong, Xiaotian Zhang, Lei Tang, Lin Shen, CT-based delta radiomics in predicting the prognosis of stage IV gastric cancer to immune checkpoint inhibitors, Frontiers in Oncology, DOI: 10.3389/fonc.2022.1059874, 2023.
21. Zhengyi Li, Bin Dong and Yanli Wang, Learning Invariance Preserving Moment Closure Model for Boltzmann-BGK Equation, Communications in Mathematics and Statistics, 11(1), 59101,2023 (arXiv:2110.03682).
22. Yang Chen, Keren Jia, Yu Sun, Cheng Zhang, Yilin Li, Li Zhang, Zifan Chen, Jiangdong Zhang, Yajie Hu, Jiajia Yuan, Xingwang Zhao, Yanyan Li, Jifang Gong, Bin Dong, Xiaotian Zhang, Jian Li and Lin Shen, Predicting response to immunotherapy in gastric cancervia multi-dimensional analyses of the tumour immune microenvironment, Nature Communications, 13:4851, 2022.
23. Qilin Zhang, Peng Bao, Ang Qu, Weijuan Jiang, Ping Jiang, Hongqing Zhuang, Bin Dong, Ruijie Yang, The feasibility study on the generalization of deep learning dose prediction model for volumetric modulated arc therapy of cervical cancer, Journal of Applied Clinical Medical Physics, 23(6), e13583, 2022.
24. Chenglong Bao, Jian-Feng Cai, Jae Kyu Choi, Bin Dong, and Ke Wei, Improved Harmonic Incompatibility Removal for Susceptibility Mapping via Reduction of Basis Mismatch, Journal of Computational Mathematics, 40(6), 914-937, 2022.
25. Stefan C. Schonsheck, Bin Dong and Rongjie Lai, Parallel Transport Convolution: A New Tool for Convolutional Neural Networks on Manifolds, SIAM Journal on Imaging Science, 15(1), pp. 367386, 2022 (arXiv:1805.07857).
26. Yuyan Chen, Bin Dong, Jinchao Xu, Meta-MgNet: Meta Multigrid Networks for Solving Parameterized Partial Di erential Equations, Journal of Computational Physics, 455, 110996, 2022 (arXiv:2010.14088).
27. Jin Zhao, Weifeng Zhao, Zhiting Ma, Wen-An Yong, Bin Dong, Finding Models of Heat Conduction via Machine Learning, International Journal of Heat and Mass Transfer, 185, 122396, 2022.
28. Ziju Shen, Yufei Wang, Dufan Wu, Xu Yang and Bin Dong, Learning to Scan: A Deep Reinforcement Learning Approach for Personalized Scanning in CT Imaging, Inverse Problems and Imaging, 16 (1), 179, 2022 (arXiv:2006.02420).