邮箱：tanhaining@ict.ac.cn

简介：

谭海宁，副研究员，博士毕业于中国科学院大学。聚焦于计算机体系结构与天基计算系统，致力于融合软硬件特性，实现高效的天基智能计算系统设计与优化。他深入探索硬件/电路机理与计算模型的融合，推动面向新一代高效能天基芯片的研发，并促进其在天基智能体推理优化等场景中的深度应用。

谭海宁博士近年主持或参与国家专项项目、国家重点研发计划、科学院战略先导计划等科研任务10余项，先后在WWW、TVLSI、TGRS、JCST等国内外顶级期刊会议发表论文10余篇，发明型专利10余项。曾获中国计算机学会容错计算专委40周年代表性成果奖（2025）、IEEE MDM Best Paper Runner-up奖（2021）、KSEM Best Paper Runner-up奖（2018）等荣誉。

研究方向：

（1）天基计算系统的软硬件协同设计方法、计算机体系结构及高效能芯片集成；

（2）面向天基智能计算的硬件/电路机理与计算模型深度融合技术及新型天基芯片架构；

（3）基于高效能天基芯片的天基智能体推理优化算法与自适应闭环计算系统。

现面向具有强烈科研热情的优秀人才（硕士生、博士后、科研助理及实习生）开放招募！

简历投递：tanhaining@ict.ac.cn

Tan Hai-Ning, Associate Researcher. He received his Ph.D. from the University of Chinese Academy of Sciences. His research focuses on computer architecture and space-based computing systems, dedicated to integrating hardware and software characteristics to achieve efficient design and optimization of space-based intelligent computing systems. He deeply explores the fusion of hardware/circuit mechanisms with computational models, promotes the development of next-generation high-efficiency space-based chips, and facilitates their deep application in scenarios such as inference optimization for space-based intelligent agents.

In recent years,Dr. Tan has recently presided over or participated in more than 10 research tasks, including national special projects, National Key R&D Programs, and the Strategic Priority Research Program of the Chinese Academy of Sciences. He has published over 10 papers in top-tier journalsorconferences such as WWW, TVLSI, TGRS, and JCST, and holds more than 10 invention patents. His honors include the 40th Anniversary Representative Achievement Award of the CCF Technical Committee on Fault-Tolerant Computing (2025), the IEEE MDM Best Paper Runner-up Award (2021), and the KSEM Best Paper Runner-up Award (2018).

Research Interests:

(1) Software-hardware co-design methods, computer architecture, and high-efficiency chip integration for space-based computing systems;

(2) Deep fusion technologies of hardware/circuit mechanisms and computational models, along with novel space-based chip architectures for space-based intelligent computing;

(3) Inference optimization algorithms and adaptive closed-loop computing systems for space-based intelligent agents based on high-efficiency space-based chips.

Group openings: We are currently recruiting outstanding talents ( Master’s students, postdocs, research assistants, and interns) with a strong passion for scientific research!

代表作：

He, X., Liu, K., Gu, T., Liao, G., Zhu, S., Xu, J., Tan，H. & Qiu, J, "Ground Moving Target Detection With Adaptive Data Reconstruction and Improved Pseudo-Skeleton Decomposition", in IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1-14, 2024.

Guo, Z., Chang, L., Liu J., Tan, H. et al. "SENTRY: Lifetime Secure Technique for Industry Embedded Non-volatile Random-Access Memory", in Journal of Computer Science and Technology, 33(1): 1–19 January 2024.

Wang, Y., Chang, L., Wang, J., Tan, H., Han, Y. et al. "PIPECIM: Energy-Efficient Pipelined Computing-in-Memory Computation Engine with Sparsity-Aware Technique", in IEEE Transactions on Very Large Scale Integration Systems, 2024.

Liu, K., He, X., Liao, G., Zhu, S., Tan，H. & Qiu, J, "Multi-channel SAR-GMTI Algorithm Based on Adaptive Data Reconstruction and Improved RPCA", in IEEE Transactions on Geoscience and Remote Sensing, 2025.

Zhao, P., Xue D., Wu, L., Chang, L., Tan, H., Han, Y. et al."HEAT: Efficient Vision Transformer Accelerator with Hybrid-Precision Quantization", in IEEE Transactions on Circuits and Systems-II: Express Briefs, 2025.

Li, W., Yao, D., Gong, C., Jing, Q., Zhao, S., Wu, R., Tan, H. et al. " Uberl: Denoised Universal User Behavior Representation Learning", in the Web Conference, 2025.

Tan, H., Li, T., Qiu, J., Liu, Y., Han, Y. Co-Design of Vision Transformers and Accelerators for Efficient Inference on Spaceborne Edge Devices, in the International Symposium on Computer Architecture, 2025.

Li, W., Yao, D., Zhao, R., Chen, W., Gong, C., Jing, Q., Tan, H. et al. STBench+: Assessing the Ability of Large Language Models in Spatio-Temporal Analysis, submitted to TKDE,2025.