联系方式

固定电话：

电子邮箱：huqinghao2014@ia.ac.cn

招生信息

招生专业：计算机应用技术、模式识别与智能系统

招生方向：大模型高效计算、神经网络压缩

个人简介（教育背景、工作经历、社会兼职等）

简介：胡庆浩,中科院自动化所复杂系统认知与决策国家重点实验室副研究员，研究方向深度神经网络轻量化，在AAAI、CVPR、TNNLS等国际高水平会议和期刊上发表论文30余篇，其中CCF A类17篇，Google Scholar引用量2200余次。

教育背景：

2016.9-2019.7中国科学院自动化研究所计算机应用技术博士

2014.9-2016.7中国科学院自动化研究所计算机应用技术硕士

2010.9-2014.7西北工业大学计算机科学与技术本科

工作经历：

2022.04-至今中国科学院自动化研究所副研究员

2019.07-2022.04中国科学院自动化研究所助理研究员

目前承担课题情况（项目负责人）

1.面向移动计算的深度神经网络自动轻量化研究，国家自然科学基金青年科学基金项目，负责人

2.输变电设备可视缺陷识别模型前端化移植技术，企业委托，负责人

3.基于轻量化模型的输电通道隐患智能分析，企业委托，负责人

4.科技创新2030-“新一代人工智能（2030）”重大项目子课题，负责人

5.国产自主可控多模态大模型关键技术及示范应用任务二：大模型高效分布式训练与压缩技术，北京市基金项目，任务负责人。

6.电力异构融合类脑计算模型研发技术，企业委托，负责人

学术成果（代表性论文、专利等）

[1]Zeyu Zhu,Fanrong Li,Gang Li,Zejian Liu,Zitao Mo,Qinghao Hu,Xiaoyao Liang,Jian Cheng. MEGA: A Memory-Efficient GNN Accelerator Exploiting Degree-Aware Mixed-Precision Quantization. The International Symposium on High-Performance Computer Architecture (HPCA), 2024.

[2]Zeyu Zhu, Fanrong Li, Zitao Mo,Qinghao Hu, Gang Li, Zejian Liu, Xiaoyao Liang, Jian Cheng. A2Q:Aggregation-Aware Quantization for Graph Neural Networks. The International Conference on Learning Representations (ICLR), 2023.

[3]Zeyu Zhu, Fanrong Li, Zitao Mo,Qinghao Hu, Gang Li, Zejian Liu, Xiaoyao Liang, Jian Cheng. A2Q:Aggregation-Aware Quantization for Graph Neural Networks. The International Conference on Learning Representations (ICLR), 2023.

[4][Zhixiang Ye*,Qinghao Hu*, Tianli Zhao, Wangping Zhou, Jian Cheng. MCUNeRF: Packing NeRF into an MCU with 1MB Memory. ACM International Conference on Multimedia(ACM MM)，2023

[5]Xiangyu Chen,Qinghao Hu, Kaidong Li, Cuncong Zhong, Guanghui Wang. Accumulated Trivial Attention Matters in Vision Transformers on Small Datasets. IEEE Winter Conference on Applications of Computer Vision (WACV)，2023

[6]Qinghao Hu, Gang Li, Qiman Wu, Jian Cheng.PalQuant: Accelerating High-Precision Networks on Low-Precision Accelerator.European Conference on Computer Vision (ECCV), 2022

[7]Qiang Chen, Qiman Wu, Jian Wang,Qinghao Hu*, Tao Hu, Errui Ding, Jian Cheng, Jingdong Wang. Mixformer: Mixing features across windows and dimension. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)，2022

[8]Xing Lan,Qinghao Hu, Jian Cheng.ATF: An Alternating Training Framework for Weakly Supervised Face Alignment. IEEE Transactions on Multimedia (TMM)，2022

[9]Tianli Zhao,Qinghao Hu, Xiangyu He, Weixiang Xu, Jiaxing Wang, Cong Leng, Jian Cheng.ECBC: Efficient convolution via blocked columnizing. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021

[10]Guan’An Wang,Qinghao Hu,Yang Yang,Jian Cheng, Zeng-Guang Hou. Adversarial Binary Mutual Learning for Semi-Supervised Deep Hashing.IEEE Transactions on Neural Networks and Learning Systems (TNNLS)，2021

[11]Qinghao Hu, Gang Li, Peisong Wang, Yifan Zhang, Jian Cheng. Training Binary Weight Networks via Semi-Binary Decomposition. European Conference on Computer Vision (ECCV), 2018

[12]Qinghao Hu, Peisong Wang, Jian Cheng. From Hashing to CNNs: Training Binary Weight Networks via Hashing. The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI), 2018

[13]Peisong Wang,Qinghao Hu, Yifan Zhang, Chunjie Zhang, Yang Liu, Jian Cheng. Two-Step Quantization for Low-bit Neural Networks. IEEE Conference on Computer Vision and Pattern Recognition(CVPR 2018)

[14]Qinghao Hu, Jiaxiang Wu, Jian Cheng, Lifang Wu, Hanqing Lu. Pseudo label based unsupervised deep discriminative hashing for image retrieval. ACM International Conference on Multimedia(ACM MM）,2017

[15]Qinghao Hu, Jiaxiang Wu, Lu Bai, Yifan Zhang, Jian Cheng. Fast k-means for large scale clustering. The 26th ACM International Conference on Information and Knowledge Management(CIKM)，2017

获奖情况

1.2019年ICCV轻量化人脸识别挑战赛第二名

2.2019年Nvidia奖学金

3.2015年MSR-Bing图像识别挑战赛第一名