特聘序列

硕士生导师，深圳理工大学人工智能研究院特聘副教授，研究聚焦于多模态大语言模型，图像分析与计算机仿真，于人工智能顶级会议及交叉期刊发表论文20篇，成果发表于International Conference on Machine Learning (ICML)、IEEE Transactions on Medical Imaging (TMI)和Journal of Biomechanics等知名期刊会议。长期担任CVPR、Medical Image Analysis等国际顶级会议及期刊审稿人。拥有丰富的产学研经验，成功研发了行业领先的多模态基础模型，与上海AI Lab合作打造了全球首个医疗多模态基础模型群浦医，同时依托上海申康医院发展中心构建了国内最大的医疗大数据训练设施。研发成果已落地为在国际国内应用的AI产品SenseCare，并在国产化方面实现突破，与华为合作完成了AI系统的国产化迁移，攻克了CUDA至昇腾平台的关键技术。

多模态世界模型，图像处理和计算机仿真。专注于多模态世界模型的高效化、可信化及实用化研究，致力于解决其计算成本、知识融合与泛化能力三大核心挑战，推动前沿技术在高频场景中的高效落地与应用普惠。研究重点包括：

1)多模态大模型的高效计算与压缩:聚焦视觉令牌冗余与计算瓶颈，研究视觉令牌压缩、动态推理等高效计算范式，并通过蒸馏、量化与神经架构搜索实现模型轻量化，构建高性能、低延迟的多模态系统。

2)数据与知识双驱动的多模态学习:探索小样本环境下结构化知识与数据的协同机制，研究跨模态提示微调、参数高效适配等技术，实现知识引导的模型压缩与任务高效迁移。

3)多模态模型的可解释性与泛化性:针对模型决策黑盒与域外泛化难题，融合思维链与强化学习构建可信推理框架，研究不确定性建模与分布外适应机制，提升模型的透明度与跨场景稳健性。

学习经历

2013.4-2017.6，上海交通大学-日本千叶大学，博士

2010.9-2013.3，上海交通大学，硕士

2005.9-2010.7，浙江大学，学士

工作经历

2025.5-至今，深圳理工大学人工智能研究院，特聘副教授

2021.3-2025.4，香港中文大学博智感知交互研究中心，研究员

2019.8-2021.2，商汤科技/复星杏脉，高级研究员

2017.7-2019.7，上海交通大学，博士后

代表性论文

1.Xiaoyu Yang, Lijian Xu*, Xingyu Zeng, Xiaosong Wang, Hongsheng Li, Shaoting Zhang. SCALAR: Scene-Aware Framework for Efficient and Generalized Spatial-Concept Alignment. Pattern Recognition.2026. (JCR一区国际期刊)

2.Zhiqiang Wang, Kunfeng Chen, Gongbin Tang, Lijian Xu*, Dongfeng Xue. From scalar indicators to full-field prediction: A multi-scale surrogate framework for thermal-field design in large-diameter Czochralski growth. Journal of Crystal Growth. 2026. 686(1). (AI4S晶体领域顶刊)

3.Xiaoyu Yang, Lijian Xu*, Hongsheng Li, Shaoting Zhang. One Leaf Reveals the Season: Occlusion-Based Contrastive Learning with Semantic-Aware Views for Efficient Visual Representation. International Conference on Machine Learning 2025. (CCF A 类国际会议)

4.Xiaoyu Yang, Lijian Xu*, Qing Xia, Simon Yu, Hongsheng Li, Shaoting Zhang. Segmentation and Vascular Vectorization for Coronary Artery by Geometry-based Cascaded Neural Network. IEEE Transactions on Medical Imaging. 2024.1:259-269. (JCR 一区, 医学影像处理顶刊)

5.Lijian Xu, Fuyou Liang, Lixu Gu, Hao Liu. Flow instability detected in ruptured versus unruptured cerebral aneurysms at the internal carotid artery. Journal of Biomechanics. 2019. 72:187–199. (JCR二区, 生物力学顶刊)

6.Lijian Xu, Fuyou Liang, Hao Liu. Influence of aging-associated flow waveform variation on hemodynamics in aneurysms present at internal carotid artery: a computational model-based study. Computers in Biology and Medicine. 2018. 101:51–60. (JCR一区国际期刊)

7.Lijian Xu, Lekang Yin, Youjun Liu, Fuyou Liang. A computational study on the influence of aortic valve disease on hemodynamics in dilated aorta. Mathematical Biosciences and Engineering. 2020. 17(1): 606-626.  (JCR二区国际期刊)

8.Lijian Xu, Tianyang Yang, Lekang Yin, Y Vassilevski, Fuyou Liang. Numerical simulation of blood flow in aorta with dilation: a comparison between laminar and LES modeling methods. Computer Modeling in Engineering & Sciences. 2020. 124(2): 509-526. (JCR二区国际期刊)

9.Lijian Xu, Fuyou Liang, Bing Zhao, Hao Liu. Morphological and hemodynamic factors associated with ruptured middle cerebral artery mirror aneurysms: a retrospective study. World Neurosurgery. 2020. 137: e138-e143. (JCR二区国际期刊)

10.Lijian Xu, Lixu Gu, Hao Liu. Exploring potential association between flow instability and rupture in patients with matched-pairs of ruptured–unruptured intracranial aneurysms. Biomedical Engineering Online. 2016. 15: 461-477. (JCR二区国际期刊)

11.Lijian Xu, Michiko Sugawara, Gaku Tanaka, Hao Liu. Effect of elasticity on wall shear stress inside cerebral aneurysm at anterior cerebral artery. Technology and Health Care. 2016. 24(3): 349-357.(SCI国际期刊)

12.Lijian Xu, Bing Zhao, Fuyou Liang. Computational methods applied to analyze the hemodynamic effects of flow-diverter devices in the treatment of cerebral aneurysms: current status and future directions. Medicine in Novel Technology and Devices. 2019. 3: 100018.

13.Lijian Xu, Atsushi Saito, Yoko Yokoyama, Hao Liu. Low-frequency harmonics in inlet flow rate play a crucial role in inducing flow instabilities in terminal cerebral aneurysms. Journal of Biomechanical Science and Engineering.  2016. 11(3): 16-00117-16-00117.

14.Lijian Xu, Jun Liu, Weiwei Zhan, Lixu Gu. A novel algorithm for CT-ultrasound registration. IEEE EMBS Point-of-Care Healthcare Technologies. 2013. (SCI国际期刊)

15.Xiaoyu Yang, Lijian Xu*, Qing Xia, Simon Yu, Hongsheng Li, Shaoting Zhang.  Geometry-based end-to-end segmentation of coronary artery in computed tomography angiography. International Workshop on Trustworthy Machine Learning for Healthcare. 2023: 190-196.(CCF A 类国际会议，workshop)

16.Ziyu Ni, Linda Wei, Lijian Xu*, Qing Xia, Hongsheng Li, Shaoting Zhang, Dimitris Metaxas. Voxel2hemodynamics: An end-to-end deep learning method for predicting coronary artery hemodynamics. International Workshop on Statistical Atlases and Computational Models of the Heart. 2023: 15-24. (CCF B 类国际会议，workshop)

17.Lijian Xu, Lekang Yin, Fuyou Liang. Comparison of Aortic Flow patterns in Patients with and without Aortic Valve Disease: Hemodynamic Simulation based on PC-MRI and CTA data. The first international symposium on Biomechanics and Mechanobiology in Cardiovascular System, 18-20 Dec 2018. Nanjing, China.(国内会议)

18.Lijian Xu, Fuyou Liang, Hao LIu. Waveform dependence of hemodynamic factors in cerebral aneurysms at internal carotid artery, 8th World Congress of Biomechanics, 8-12 July 2018. Dublin, Ireland. (国际会议)

19.Lijian Xu, Hao Liu. Flow instability may not closely correlate with the rupture of cerebral aneurysms at the internal carotid artery. 5th International Conference on Computational and Mathematical Biomedical Engineering. 10-12 April 2017. Pittsburgh, United States.(国际会议)

20.Lijian Xu, Hao Liu.  Association between flow instability and rupture of intracranial cerebral aneurysms：effects of low frequency harmonics in inlet flow rate, The 39th Japanese Society of Biorheology, 18-19 June 2016. Tokyo, Japan.(国际会议)

21.Lijian Xu, Hao Liu. The effect of inlet waveform on computational hemodynamics of intracranial aneurysms. 4th International Conference on Computational and Mathematical Biomedical Engineering. 29 June -1 July 2015. Cachan, France.(国际会议)

22.Lijian Xu, Hao Liu. Simulation-based Prediction of Occlusion inside Cerebral Aneurysm at Bifurcation of Anterior Communicating Artery, 7th World Congress of Biomechanics, 6-11 July 2014. Boston, United States.(国际会议)

23.Zhiqiang Zhang, Lijian Xu, Rong Liu, Fuyou Liang. Importance of incorporating systemic cerebroarterial hemodynamics into computational modeling of blood flow in intracranial aneurysm. Journal of Hydrodynamics. 2020. 32:510-522. (JCR一区国际期刊)

24.Xuanyu Li, Xiaosheng Liu, Lijian Xu, Fuyou Liang, Bing Zhao, Hao Liu. Tortuosity of the superficial femoral artery and its influence on blood flow patterns and risk of atherosclerosis. Biomechanics and Modeling in Mechanobiology. 2019, 18: 883-896. (JCR一区国际期刊)

25.Xingdong Zhou, Lekang Yin, Lijian Xu, Fuyou Liang, Bing. Non-periodicity of blood flow and its influence on wall shear stress in the carotid artery bifurcation. Journal of Biomechanics. 2020, 101: 109617. (JCR二区, 生物力学顶刊)

26.Zhuowei Li, Qing Xia,..Lijian Xu, Shaoting Zhang. A Deep Reinforced Tree-traversal Agent for Coronary Artery Centerline Extraction. MICCAI, 2021: 418-428. (CCF B类国际会议, 医学影像AI顶会)

27.Debao Guan,Yuqian Mei, Lijian Xu, Li Cai, Xiaoyu Luo, Hao Gao. Effects of dispersed fibres in myocardial mechanics, Part I: passive response. Mathematical Biosciences and Engineering, 19(4), 3972-3993. (JCR二区国际期刊)

28.Debao Guan, Yingjie Wang, Lijian Xu, Li Cai, Xiaoyu Luo, Hao Gao. (2022). Effects of dispersed fibres in myocardial mechanics, Part II: active response. Mathematical Biosciences and Engineering, 19(4), 4101-4119. (JCR二区国际期刊)

29.Lin Qi, Jie-ying Liang,.. Lijian Xu, Bao-cai Xing, Xin Wang, Yu-hong Li.Deep learning-derived spatial organization features on histology images predicts prognosis in colorectal liver metastasis patients after hepatectomy. Iscience, 2023, 26(10). (JCR一区国际期刊)

成果转化:

1.医学图像重建与诊断系统：开发血管分割及脑出血识别算法，首创基于深度学习的ASPECTS区域自动评分技术，脑卒中量化评估准确率达94.5%，通过NMPA二类证认证。

2.功能学参数计算系统：构建CT影像的血流动力学分析引擎，实现血管流速、FFR及脑灌注核心区AI定量，核心/半暗带体积测算误差<5%。

3.智能医学研究平台（上海申康）：研发支持多模态的医疗大数据训练框架，开发胸肺疾病多模态诊断系统，临床准确率93.2%。

4.国产化AI系统迁移（华为昇腾）：解决CUDA至昇腾Atlas300芯片的算子适配技术，识别准确率95.3%，获华为昇腾技术认证。

5.AI临床验证：在香港屯门医院建立肺结节AI双盲验证方案，敏感性达97.3%，形成香港医管局认证的申报标准。