您当前的位置:
何振梁
何振梁 副研究员
电子邮箱: hezhenliang@ict.ac.cn
通讯地址: 北京市海淀区科学院南路6号
研究方向: 生成式模型;世界模型;计算机视觉
个人简介

个人主页:https://lynnho.github.io 

GitHub:https://github.com/LynnHo, https://github.com/VIPL-GENUN

谷歌学术:https://scholar.google.com/citations?user=fDTTEaAAAAAJ


经历

2025.10 — 今:中国科学院计算技术研究所,副研究员

2023.04 — 2025.10:中国科学院计算技术研究所,助理研究员

2021.08 — 2023.03:京东公司,算法工程师

2015.09 — 2021.06:中国科学院计算技术研究所,博士生

2011.09 — 2015.06:北京邮电大学,信息与通信工程学院,本科生

学术服务
研究内容
邀请报告与论著

论文完整列表请参见:https://scholar.google.com/citations?user=fDTTEaAAAAAJ

[1] Yifeng Xu, Zhenliang He, Shiguang Shan, Xilin Chen. CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation. International Conference on Learning Representations (ICLR), 2025.

[2] Boyuan Zhang, Zhenliang He, Meina Kan, Shiguang Shan. Precise Integral in NeRFs: Overcoming the Approximation Errors of Numerical Quadrature. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025.【Oral】

[3] Zhenliang He, Meina Kan, Shiguang Shan. EigenGAN: Layer-Wise Eigen-Learning for GANs. IEEE International Conference on Computer Vision (ICCV), 2021.

[4] Zhenliang He, Meina Kan, Shiguang Shan, Xilin Chen. S2GAN: Share Aging Factors Across Ages and Share Aging Trends Among Individuals. IEEE International Conference on Computer Vision (ICCV), 2019.【Oral】

[5] Zhenliang He, Wangmeng Zuo, Meina Kan, Shiguang Shan, Xilin Chen. AttGAN: Facial Attribute Editing by Only Changing What You Want. IEEE Transactions on Image Processing (TIP), 2019. 【ESI高被引】