王智

王智，清华大学深圳国际研究生院副教授，从事多媒体网络和系统方向研究，包括高性能数据处理系统优化、分布式机器学习系统、边缘计算与网络等。先后获得2017年教育部自然科学奖一等奖，2018年国家自然科学二等奖，2019年深圳市青年科技奖，2020年中国电子学会技术发明一等奖，入选中组部万人计划。研究成果获得多媒体领域高水平会议ACM Multimedia最佳论文奖（国内高校首次第一单位获得），2014年计算机学会优秀博士论文奖（全国十人）。担任IEEE TMM副编辑和ACM TIST客座编辑。关键技术获得2014年移动互联网创业大赛第一名（全国300所高校1200团队参加）。王智研究成果获得工业届广泛应用和关注，相关成果以第一完成人授权专利10余项；数据驱动的无线网络性能预测技术被知名技术媒体MIT Technology Review、Synced Review等报道，成为业界重要参考。

2008/09 –2014/01，清华大学，计算机科学与技术系，博士（硕博连读）

2004/09 – 2008/09，清华大学，计算机科学与技术系，学士

2019/3至今：清华大学深圳国际研究生院，副教授

2018/12至2019/3：清华大学深圳研究生院，副教授

2014/02至2018/12：清华大学深圳研究生院，讲师

2019.11至今：IEEE Transactions on Multimedia, Associate Editor

2019.7至今：IEEE Open Journal of Communications, Associate Editor

2015至2018：计算机科学技术学报（JCST），客座编辑

2016至2017：ACM Transactions on Intelligent Systems and Technology (ACM TIST)，客座编辑

2014至今：计算机学会多媒体专业委员会，委员

2018至今：中国通信学会云计算和大数据应用委员会，委员

2018至今：电子学会网络多媒体专委会，委员

一、基于多媒体智能的边缘计算：现有边缘计算和网络架构缺少智能化拓扑和策略支持，运行效率低；拟开展媒体智能分析驱动的边缘计算，主要内容包括场景感知的端边侧自动部署，算网联合的拓扑自动生成，面向边缘计算的决策大模型，以及基于元知识的边缘架构演化。

二、面向边缘计算的分布式机器学习：现有分布式机器学习框架无法适应新型边缘计算架构，导致训练与决策效率低；拟开展面向边缘计算的分布式机器学习，主要内容包括设备与拓扑感知的分布式训练，面向异构数据分布的传输优化，面向云边端架构的模型压缩与部署，以及场景感知的自适应在线决策。

“互联网视频在线转码、分发关键技术与应用”，中国电子学会技术发明一等奖，2020/12/12

万人计划青年人才项目，2019年度

“大规模多媒体的资源跨域协同计算理论方法”，国家自然科学奖二等奖，2018/12/12

“大规模多媒体的资源跨域协同计算理论方法”，教育部自然科学奖一等奖，2018/2

深圳市青年科技奖，2019

清华大学先进工作者，清华大学，2017

中国计算机学会优秀博士论文奖，中国计算机学会，2014

Best Paper Award, ACM Multimedia, 2012

Best Student Paper Award, MMM 2015

Best Paper Award, ACM Multimedia 2021, HUMA Workshop 2021

出版物

1. Jinmin Li, Tao Dai, Mingyan Zhu, Bin Chen, Zhi Wang and Shutao Xia. FSR: A General Frequency-oriented Framework to Accelerate Image Super-resolution Networks, In Proceedings of Thirty-Seventh AAAI Conference on Artificial Intelligence, Washiongton, DC, USA, 7-14 February 2023 (CCF-A)

2. Zijie Fang, Yang Chen, Yifeng Wang, Zhi Wang, Xiangyang Ji and Yongbing Zhang. Weakly-Supervised Semantic Segmentation for Histopathology Images Based on Dataset Synthesis and Feature Consistency Constraint, In Proceedings of Thirty-Seventh AAAI Conference on Artificial Intelligence, Washiongton, DC, USA, 7-14 February 2023 (CCF-A)

3. Xiaohan Lan, Yitian Yuan, Hong Chen, Xin Wang, Zequn Jie, Lin Ma, Zhi Wang and Wenwu Zhu. Curriculum Multi-Negative Augmentation for Debiased Video Grounding, In Proceedings of Thirty-Seventh AAAI Conference on Artificial Intelligence, Washiongton, DC, USA, 7-14 February 2023 (CCF-A)

4. Yiyun Lu, Yifei Zhu and Zhi Wang. Personalized 360-Degree Video Streaming: A Meta-Learning Approach, In Proceedings of ACM Multimedia, Lisbon, Portugal, 10-14 October 2022 (CCF-A)

5. Chen Tang, Haoyu Zhai, Kai Ouyang, Zhi Wang, Yifei Zhu and Wenwu Zhu. Arbitrary Bit-width Network: A Joint Layer-Wise Quantization and Adaptive Inference Approach, In Proceedings of ACM Multimedia, Lisbon, Portugal, 10-14 October 2022 (CCF-A)

6. Chen Tang, Kai Ouyang, Zhi Wang, Yifei Zhu, Wen Ji, Yaowei Wang and Wenwu Zhu. Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance, In Proceedings of European Conference on Computer Vision (ECCV), Tel-Aviv, Israel, 23-27 October 2022

7. Xinjie Yuan, Mingzhou Wu, Zhi Wang, Yifei Zhu, Ming Ma, Junjian Guo, Zhili Zhang and Wenwu Zhu. Understanding 5G Performance for Real-world Services: a Content Provider's Perspective, In Proceedings of ACM SIGCOMM, Amsterdam, the Netherlands, August 2022 (CCF-A)

8. Cheng Chen, Yichun Yin, Lifeng Shang, Xin Jiang, Yujia Qin, Fengyu Wang, Zhi Wang, Xiao Chen, Zhiyuan Liu and Qun Liu. bert2BERT: Towards Reusable Pretrained Language Models, In Proceedings of Annual Meeting of the Association for Computational Linguistics (ACL), Dublin, 22-27 May 2022 (CCF-A)

9. Shuzhao Xie, Yuan Xue, Yifei Zhu and Zhi Wang. Cost Effective MLaaS Federation: A Combinatorial Reinforcement Learning Approach, In Proceedings of IEEE INFOCOM, Virtual Conference, 2-5 May 2022 (CCF-A) [project]

10. Lei Zhang, Yuqing Zhang, Ximing Wu, Fangxin Wang, Laizhong Cui, Zhi Wang and Jiangchuan Liu. Batch Adaptative Streaming for Video Analytics, In Proceedings of IEEE INFOCOM, Virtual Conference, 2-5 May 2022 (CCF-A)

11. Zhiwei Hao, Yong Luo, Zhi Wang, Han Hu and Jianping An. CDFKD-MFS: Collaborative Data-Free Knowledge Distillation via Multi-Level Feature Sharing, In IEEE Transactions on Multimedia (TMM), vol. 24, no. xx, pp. 4262-4274, 2022.

12. Xiaohan Lan, Yitian Yuan, Xin Wang, Long Chen, Zhi Wang, Lin Ma and Wenwu Zhu. A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach, In ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), vol. xx, no. xx, article xx, Accepted.

13. Zhiwei Cao, Xin Zhou, Han Hu, Zhi Wang and Yonggang Wen. Towards a Systematic Survey for Carbon Neutral Data Centers, In IEEE Communications Surveys and Tutorials, vol. xx, no. xx, article xx, Accepted. (Impact Factor: 25.25 as of April 2022)

14. Shiji Zhou, Lianzhe Wang, Shanghang Zhang, Zhi Wang and Wenwu Zhu. Active Gradual Domain Adaptation: Dataset and Approach, In IEEE Transactions on Multimedia, vol. 24, pp. 1210--1220, January 2022. (JCR-Q1)

15. Jingyan Jiang, Ziyue Luo, Chenghao Hu, Zhaoliang He, Zhi Wang, Shutao Xia and Chuan Wu. Joint Model and Data Adaptation for Cloud Inference Serving, In Proceedings of IEEE Real-Time Systems Symposium (RTSS), Dortmund, Germany, 7–10 December 2021 (CCF-A)

16. Tao Dai, Yalei Lv, Bin Chen, Zhi Wang, Zexuan Zhu and Shutao Xia. Mix-order Attention Networks for Image Restoration, In Proceedings of ACM Multimedia, Chengdu, China, 20-24 October 2021 (CCF-A)

17. Yitian Yuan, Xiaohan Lan, Xin Wang, Long Chen, Zhi Wang and Wenwu Zhu. A Closer Look at Temporal Sentence Grounding in Videos: Dataset and Metric, In Proceedings of ACM Multimedia, HUMA Workshop, Chengdu, China, 20–24 October 2021 (Best Paper Award)

18. Jiahui Ye, Zichun Li, Zhi Wang, Zhuobin Zheng, Han Hu and Wenwu Zhu. Joint Cache Size Scaling and Replacement Adaptation for Small Content Providers, In Proceedings of IEEE INFOCOM 2021, Virtual Conference, China, May 10--13, 2021 (CCF-A)

19. Haopeng Yan, Zeming Chen, Zhi Wang and Wenwu Zhu. DRL-based Collaborative Edge Content Replication with Popularity Distillation, In Proceedings of IEEE ICME, Shenzhen, China, July 5-9, 2021

20. Zhiwei Hao, Yong Luo, Zhi Wang, Han Hu and Jianping An. Model Compression via Collaborative Data-free Knowledge Distillation for Edge Intelligence, In Proceedings of IEEE ICME, Shenzhen, China, July 5-9, 2021 (Best Paper Award Finalist)

21. Shiji Zhou, Zhi Wang, Chenghao Hu, Yinan Mao, Haopeng Yan, Chuan Wu, Shanghang Zhang and Wenwu Zhu. Caching in Dynamic Environments: a Near-optimal Online Learning Approach, In IEEE Transactions on Multimedia, vol. 23, no. 8, pp. 1--13, March 2021. (JCR-Q1)

22. Laizhong Cui, Erchao Ni, Yipeng Zhou, Zhi Wang, Lei Zhang, Jiangchuan Liu and Yuedong Xu. Towards Real-Time Video Caching at Edge Servers: A Cost-Aware Deep Q-Learning Solution, In IEEE Transactions on Multimedia, vol. xx, no. xx, pp. xx--xx, November 2021 (accepted). (JCR-Q1)

23. Zhaoliang He, Hongshan Li, Zhi Wang, Shutao Xia and Wenwu Zhu. Adaptive Compression for Online Computer Vision: An Edge Reinforcement Learning Approach, In ACM Transactions on Multimedia Computing, Communications, and Applications, vol. 17, no. 4, article 118, September 2021.

24. Cheng Zhan, Han Hu, Zhi Liu, Zhi Wang and Shiwen Mao. Multi-UAV-Enabled Mobile Edge Computing for Time-Constrained IoT Applications, In IEEE Internet of Things Journal, vol. 8, no. 20, pp. 15553--15567, October 2021

25. Wenwu Zhu and Zhi Wang. Data-driven Multiemdia Edge Network and Content Delivery, In Science China Information Sciences, vol. 51, no. 3, pp. 468--504, 2021 (CCF-A)

我们正在招募博士、硕士研究生候选人，对数据驱动多媒体网络、移动云计算和大数据系统有兴趣的同学，请将您的简历通过电子邮件发送给我。