刁博宇  高级工程师  

研究方向:

所属部门:装备智能系统研究中心

导师类别:硕导计算机系统结构

联系方式:diaoboyu2012@ict.ac.cn

个人网页:https://people.ucas.edu.cn/~bydiao

简       历:

2021年9月 — 今:中国科学院计算技术研究所,高级工程师

2018年7月 — 2021年9月:中国科学院计算技术研究所,助理研究员

2012年9月 — 2018年6月:中国科学院计算技术研究所,博士研究生

2008年9月 — 2012年7月:北京理工大学,计算机学院,本科生

主要论著:

[1] L Dai, L Gong, Z An, Y Xu, B Diao, Sketch-Fusion: A Gradient Compression Method with Multi-Layer Fusion for Communication-Efficient Distributed Training, Journal of Parallel and Distributed Computing, 2024(185).

[2] LHuang, Y Zeng, C Yang, Z An, B Diao and Y Xu, eTag: Class-Incremental Learning via Embedding Distillation and Task-Oriented Generation, The Thirty-Eighth AAAI Conference on Artificial Intelligence 2024, AAAI-2024.

[3] C Yang, ZAn, L Huang, J Bi, X Yu, H Yang, B Diao, YXu, CLIP-KD: An Empirical Study of CLIP Model Distillation, The IEEE / CVF Computer Vision and Pattern Recognition Conference2024, CVPR-2024.

[4] D Dong, H Jiang, B Diao, AKGF: Automatic Kernel Generation for DNN on CPU-FPGA,The Computer Journal, 2023 (86).

[5] Y Yao, Z Zhang, K Yang, H Liang, Q Yan, F Zhuang, B Diao, Y Xu and C Li, A Knowledge Enhanced Hierarchical Fusion Network for CTR Prediction under Account Search Scenario in WeChat, International World Wide Web Conference 2023.WWW-2023.

[6] Q Wang, T Li, Y Xu, F Wang, B Diao, L Zheng, J Huang, How to prevent malicious use of intelligent unmanned swarms?The Innovation, 2023, 4 (2)

[7] K Yao, J Wang, B Diao, C Li, Towards Understanding the Generalization of Deepfake Detectors from a Game-Theoretical View, IEEE/CVF International Conference on Computer Vision2023. ICCV-2023.

[8] C Li, K Yao, J Wang, B Diao, Y Xu, Q Zhang,Interpretable Generative Adversarial Networks,The Thirty-Sixth AAAI Conference on Artificial Intelligence. AAAI-22.

[9] Q Li, Z Zhang, B Diao, Y Xu, C Li, Towards Understanding the Effect of Node Features on the Predictions of Graph Neural Networks, International Conference on Artificial Neural Networks, ICANN-22.

[10] J Xu, B Diao, B Cui, K Yang, C Li, YXu, Pruning Filter via Gaussian Distribution Feature for Deep Neural Networks Acceleration, International Joint Conference on Neural Networks.IJCNN-22.

[11] J. Xu, B. Diao, B. Cui, C. Li, Y. Xu, and H. Hong, Analysis Of The Influence Degree Of Network Pruning On Fine-grained Image Processing Tasks. 2021 6th International Conference on Signal and Image Processing. ICSIP-21.(Best Presentation Award)

[12] F. Wang, B. Diao, T. Sun, and Y. Xu, "Data Security and Privacy Challenges of Computing Offloading in FINs," IEEE Network, vol. 34, no. 2, pp. 14-20, 2020.

[13] B. Diao, K. Yang, Y. Mei, Q. Wang, C. Li, and Y. Xu, A scalable testbed for task offloading and deployment of heterogeneous edge computing, in IEEE International Conferences on Ubiquitous Computing and Communications.IUCC-19.

[14] C. Yang, Z. An, C. Li, B. Diao, and Y. Xu, "Multi-objective Pruning for CNNs Using Genetic Algorithm," in 28th International Conference on Artificial Neural Networks, ICANN-19.

[15] Q. Xie, C. Li, B. Diao, Z. An, and Y. Xu, "L0 Regularization based Fine-grained Neural Network Pruning Method," in 11th International Conference on Electronics, Computers and Artificial Intelligence. ECAI-19.

[16] B. Diao, Y. Xu, C. Li, Z. An, Q. Wang, and Z. Chen, "A nearest neighbor regression-based channel estimation algorithm for acoustic channel-aware routing," in 2018 OCEANS - MTS/IEEE Kobe Techno-Oceans. OCEANS-18.

[17] B. Diao, Y. Xu, Q. Wang, Z. Chen, C. Li, Z. An, and G. Han, "A reliable depth-based routing protocol with network coding for underwater sensor networks," in 22nd IEEE International Conference on Parallel and Distributed Systems.ICPADS-16.

部分专利:

[1] 一种边缘数据管理方法、介质、边缘服务器和系统,专利号:202010588987.9 

[2] 一种基于深度强化学习的集群任务调度方法及系统,专利号:202211363177.9

[3] 一种轻量级多任务视频流实时推理方法及系统,专利号:202211348871.3

[4] 一种搜索卷积神经网络的方法,专利号:202010012084.6

[5] 面向海量轨迹点数据的时空索引构建方法,专利号:201710270989.1

科研项目:


获奖及荣誉:

[1]2020年,中国指挥与控制学会科学技术进步奖,二等奖

[2]20192022年,中国科学院计算技术研究所,优秀科研人员

[3]2018年,北京市优秀毕业生

[4]2017年,国家奖学金博士生奖