寇明阳，工学博士，北京科技大学计算机与通信工程学院特聘副教授，北京科技大学-华大九天联合实验室骨干，本科与博士毕业于清华大学计算机科学与技术系，目前在北京科技大学姚海龙教授团队继续从事集成电路相关研究。曾参与科技部2030“新一代人工智能”重大项目、国家自然科学基金重点项目、国家自然科学基金面上项目等。主要研究方向为集成电路设计及应用，包括人工智能芯片编译器、布局布线算法等。在CCF A类会议、期刊上以第一作者/共同第一作者身份发表多篇论文，包括DAC、TCAD、NeurIPS等。

邮箱：kmy@ustb.edu.cn

发表论文：

[1]  M. Kou, J. Gu, S. Wei, H. Yao and S. Yin, “TAEM: Fast Transfer-Aware Effective Loop Mapping for Heterogeneous Resources on CGRA,” 2020 57th ACM/IEEE Design Automation Conference (DAC), 2020.

[2]  M. Kou, J. Gu, S. Wei, H. Yao and S. Yin, “TAEM 2.0: A Faster Transfer-Aware Effective Loop Mapping for Heterogeneous Resources on CGRA,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 42, no. 8, pp. 2552-2565, Aug. 2023, doi: 10.1109/TCAD.2022.3226152.

[3]  M. Kou, J. Zeng, B. Han, F. Xu, J. Gu and H. Yao, “GEML: GNN-Based Efficient Mapping Method for Large Loop Applications on CGRA,” 2022 59th ACM/IEEE Design Automation Conference (DAC), 2022.

[4]  M. Kou, P. -Y. Cheng, J. Zeng, T. -Y. Ho, K. Takagi and H. Yao, “Splitter-Aware Multiterminal Routing With Length-Matching Constraint for RSFQ Circuits,” in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 40, no. 11, pp. 2251-2264, Nov. 2021.

[5]  J. Zeng, M. Kou and H. Yao, “Neuroschedule: A novel effective gnn-based scheduling method for high-level synthesis,” Advances in Neural Information Processing Systems, 2022, 35: 23792-23804. （Spotlight论文，共同第一作者）

[6]  曾军，寇明阳，郑惜元，姚海龙，孙富春，“TVM_T: 基于 TVM 的高性能神经网络训练编译器,” 中国科学：信息科学，2023 年，第 53 卷，第 12 期: 2458–2471.

[7]  J. Zeng, M. Kou and H. Yao, “KunlunTVM: A Compilation Framework for Kunlun Chip Supporting Both Training and Inference,” ACM Great. Lakes Symposium on VLSI (GLSVLSI 2022).