讲座时间：2024 年 11 月 11 日 13： 30 —17：00

讲座地点：沙河校区信息楼 XXC-305

讲座内容简介：

1、The progress in first-principles simulation codes and supercomputing capabilities have given birth to the so-called high-throughput (HT) ab initio approach, thus allowing for the identification of many new compounds for a variety of applications (e.g., lithium battery and photovoltaic). As a result, a number of databases have also become available online, providing access to various properties of materials, mainly ground‑state though. Indeed, for more complex properties (e.g., linear or higher‑order responses), the HT approach is still out of reach because of the required CPU time. To overcome this limitation, machine learning approaches have recently attracted much attention in the framework of materials design.

2、扩散生成模型在图像反问题计算中的应用。 图像反问题计算的关键是图像先验表示的设计。随着近来年深度学习的发展，图像先验从传统的专家设计、数据驱动等表示，逐步发展到基于生成模型学习的表示。更精确的图像先验无疑能带来图像反问题计算的性能提升。本报告先简单介绍扩散生成模型学习数据分布的范式，然后我们介绍扩散生成模型的数学建模以及如何发展基于扩散生成模型的反问题计算算法。扩散生成模型的迭代生成特性与反问题的迭代算法能很好地融合，而问题的关键是如何从数学上导出反问题的扩散生成式算法。本报告将介绍图像反问题的生成式算法的主要思想和计算框架。

3、Computational Imaging and Computational Radiotherapy。Medical imaging, medical image analysis, and radiotherapy planning are fundamental computational tasks within radiotherapy, directly impacting treatment accuracy. Over recent years, my focus has been on developing high-dimensional image processing and reconstruction methods. More recently, our research has shifted towards addressing mathematical challenges in advanced imaging and radiotherapy. In this talk, I will provide a quick overview of our previous work in reconstruction and medical image analysis. These efforts have been instrumental in refining radiotherapy dose distributions for enhanced interpretability by clinicians. Furthermore, I will discuss our ongoing efforts to synergize imaging techniques with advanced image analysis methods. Specifically, I will present solve results demonstrating our approach to efficiently and robustly solve challenges in Flash radiotherapy planning and Robust radiotherapy planning.

主讲人简介：

G.-M. Rignanese is Professor at the Ecole Polytechnique de Louvain (EPL) and Research Director at the F.R.S.-FNRS. He received his Engineering degree from the Université catholique de Louvain in 1994 and Ph.D. in Applied Sciences from the Université catholique de Louvain in 1998.

李季，首都师范大学，副研究员。2017年博士毕业于北京大学计算数学专业，而后在北京计算科学研究中心和新加坡国立大学做博士后研究工作。发表图像反问题计算领域相关期刊和会议论文多篇。目前的研究兴趣是传统优化和深度学习在科学计算和图像处理中的应用。

刘九龙，中国科学院数学与系统科学研究院，副研究员。2017年博士毕业于上海交通大学数学科学学院，随后在新加坡国立大学数学系从事博士后研究。他的研究兴趣涵盖反问题与医学成像，放疗规划等方面，以及与机器学习的交叉融合。他在SIAM Journal on Imaging Sciences、Inverse Problems、IEEE Transactions on Medical Imaging 等杂志以及ICLR、 CVPR、 MICCAI等机器学习会议上发表了十多篇相关研究的论文。

主办单位：计算机学院

联系方式：王老师 80187583