邮箱：zhaoyisheng@ucas.ac.cn

简介：

赵益晟，深理工算力微电子学院-中科天算天基计算硕士班导师，中科天算科技有限公司极光实验室副主任，同时担任杭州负责人。

主要研究方向为天基计算和星上智能处理算法，主持国家重点研发计划子课题、星载智能光电感知科技专项、中国博士后科学基金面上项目和多项横向项目，入选杭州市博士后典型案例，相关研究成果获得中国计算机学会容错计算专委40周年代表性成果和2025 CCF科技创业大赛行业赛二等奖。以第一作者身份在IEEE TCSVT、IEEE TGRS、IEEE JBHI、ACM MM、MICCAI等权威期刊\会议发表论文，学术兼职包括‌中国指挥与控制学会智能可穿戴技术专委会委员、中国计算机学会容错计算专委会执行委员、《天地一体化信息网络》特刊编辑。

研究方向：

（1）天基大模型及智能体；

（2）多模态大模型抗幻觉、容错计算及高效推理；

（3）遥感影像超分辨率重建；

（4）多光谱红外影像智能分析。

简历投递：zhaoyisheng@ucas.ac.cn

Yisheng Zhao is a Master's Supervisor for the Space-based Computing Program (jointly established by the School of Computing and Microelectronics at Shenzhen University of Advanced Technology and CAS Tiansuan), the Deputy Director of the Aurora Laboratory at CAS Tiansuan Technology Co., Ltd., and the Head of its Hangzhou operations.

His primary research interests are space-based computing and on-orbit intelligent processing algorithms. He has led a sub-project of the National Key R&D Program of China, a special science and technology project on space-borne intelligent photoelectric perception, a General Program of the China Postdoctoral Science Foundation, and multiple industry-funded projects. He was recognized as a "Typical Postdoctoral Case in Hangzhou." His research achievements have earned the Representative Achievement Award for the 40th Anniversary of the CCF Technical Committee on Fault-Tolerant Computing, as well as the Second Prize in the Industry Track of the 2025 CCF Science and Technology Entrepreneurship Competition.

As the first author, he has published papers in prestigious journals and conferences, including IEEE TCSVT, IEEE TGRS, IEEE JBHI, ACM MM, and MICCAI. His academic appointments include Committee Member of the Technical Committee on Smart Wearable Technology of the Chinese Institute of Command and Control (CICC), Executive Committee Member of the Technical Committee on Fault-Tolerant Computing of the China Computer Federation (CCF), and Special Issue Editor for the journal Space-Integrated-Ground Information Networks.

Research Interests:

lSpace-based large models and AI agents;

lAnti-hallucination, fault-tolerant computing, and efficient inference for multi-modal large models;

lSuper-resolution reconstruction of remote sensing images;

lIntelligent analysis of multi-spectral and infrared images.