郑紫阳助理教授

址:上海交通大学电院1-307

话:

箱:zhengziyang@sjtu.edu.cn

研究中心:媒体信息网络研究所

个人主页:https://min.sjtu.edu.cn/

个人简介
郑紫阳,上海交通大学助理教授,博士生导师,于2017年在西安交通大学应用物理系取得学士学位,2024年在上海交通大学电子工程系取得博士学位,2024年加入上海交通大学。研究方向涉及多媒体信号处理、物理神经网络等,在Nature Machine Intelligence、Science Advances、IEEE TPAMI、IEEE TSP、ICML等知名国际期刊和会议上发表学术论文十余篇,授权中国发明专利2项、美国发明专利2项。获2022年中国电子学会科技进步二等奖(排9)。
研究领域
多媒体信号处理
研究方向
  1. 多媒体信号处理
  2. 物理(光学)神经网络
重要论文
  1. Ziyang Zheng, Zhengyang Duan, Hang Chen, Rui Yang, Sheng Gao, Haiou Zhang, and Hongkai Xiong, and Xing Lin, Dual Adaptive Training of Photonic Neural Networks, Nature Machine Intelligence 5, 10, 1119-1129.
  2. Ziyang Zheng, Wenrui Dai, Duoduo Xue, Chenglin Li, Junni Zou, and Hongkai Xiong, “Hybrid ISTA: Unfolding ISTA with Convergence Guarantees Using Free-Form Deep Neural Networks,” IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI), 2023, 45(3): 3226-3244.
  3. Tao Yan, Rui Yang, Ziyang Zheng, Xing Lin, Hongkai Xiong, and Qionghai Dai, “All-optical graph representation learning using integrated diffractive photonic computing units,”  Science Advances, 2022, 8(24): eabn7630. 
  4. Duoduo Xue, Ziyang Zheng, Wenrui Dai, Chenglin Li, Junni Zou, and Honkgai Xiong, “On the Convergence of Non-Convex Phase Retrieval with Denoising Priors,” IEEE Trans. Signal Processing (TSP), 2022, 70: 4424-4439. 
  5. Shaohui Li, Wenrui Dai, Ziyang Zheng, Chenglin Li, Junni Zou, and Hongkai Xiong, “Reversible Autoencoder: A CNN-based Nonlinear Lifting Scheme for Image Reconstruction,” IEEE Trans. Signal Processing (TSP), 2021, 69: 3117-3131.
  6. Shaohui Li, Wenrui Dai, Yimian Fang, Ziyang Zheng, Wen Fei, Hongkai Xiong, and Wei Zhang, “Revisiting Learned Image Compression With Statistical Measurement of Latent Representations, ” IEEE Trans. Circuits and Systems for Video Technology (TCSVT), 2024, 34(4): 2891-2907.
  7. Xinyu Peng, Ziyang Zheng, Wenrui Dai, Nuoqian Xiao, Chenglin li, Junni Zou, and Hongkai Xiong, “Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance, ” in International Conference On Machine Learning (ICML), Vienna, Austria, OMLR 235, 2024.