Zhengguang Zhou

Biography

Zhengguang Zhou (周争光) is a researcher at Tencent Hunyuan, working on video generation, controllable generative models and customized multimodal synthesis. He joined Tencent in 2024. Previously, he worked as an algorithm engineer at Xiaohongshu (2022 – 2024) on creator-side algorithms in the Community Department, and at Megvii Technology (2019 – 2022) in the Cloud Service Group.

He obtained his M.S. in Electronics & Communication Engineering from the University of Science and Technology of China in 2019, advised by Prof. Wengang Zhou, and his B.E. in Intelligent Science and Technology from Xidian University in 2016.

Selected Publications

2025.12

StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars

Zhiyao Sun, Ziqiao Peng, Yifeng Ma, Yi Chen, Zhengguang Zhou, Zixiang Zhou, Guozhen Zhang, Youliang Zhang, Yuan Zhou, Qinglin Lu, Yong-Jin Liu

arXiv preprint · arXiv:2512.22065 · 5 citations · arXiv

2025.06

PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement

Teng Hu, Zhentao Yu, Zhengguang Zhou, Jiangning Zhang, Yuan Zhou, Qinglin Lu, Ran Yi

arXiv preprint · arXiv:2506.07848 · 11 citations · arXiv

2025.06

OmniV2V: Versatile Video Generation and Editing via Dynamic Content Manipulation

Sen Liang, Zhentao Yu, Zhengguang Zhou, Teng Hu, Hongmei Wang, Yi Chen, Qin Lin, Yuan Zhou, Xin Li, Qinglin Lu, Zhibo Chen

arXiv preprint · arXiv:2506.01801 · 13 citations · arXiv

2025.05

Hunyuan-Game: Industrial-grade Intelligent Game Creation Model

Ruihuang Li, Caijin Zhou, Shoujian Zheng, Jianxiang Lu, Jiabin Huang, Comi Chen, Junshu Tang, Guangzheng Xu, Jiale Tao, Hongmei Wang, …, Zhengguang Zhou, …, Qinglin Lu (Hunyuan Team, 50+ authors)

arXiv preprint · arXiv:2505.14135 · 5 citations · arXiv

2025.05

HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

Teng Hu, Zhentao Yu, Zhengguang Zhou, Sen Liang, Yuan Zhou, Qin Lin, Qinglin Lu

arXiv preprint · arXiv:2505.04512 · 46 citations · arXiv Project

2025.04

InstantCharacter: Personalize Any Characters with a Scalable Diffusion Transformer Framework

Jiale Tao, Yanbing Zhang, Qixun Wang, Yiji Cheng, Haofan Wang, Xu Bai, Zhengguang Zhou, Ruihuang Li, Linqing Wang, Chunyu Wang, Qin Lin, Qinglin Lu

arXiv preprint · arXiv:2504.12395 · 17 citations · arXiv Code

2024.09

StoryMaker: Towards Holistic Consistent Characters in Text-to-Image Generation

Zhengguang Zhou, Jing Li, Huaxia Li, Nemo Chen, Xu Tang

arXiv preprint · arXiv:2409.12576 · 42 citations · arXiv Code

2020

Progressive Learning of Low-Precision Networks for Image Classification

Zhengguang Zhou, Wengang Zhou, Xutao Lv, Xuan Huang, Xiaoyu Wang, Houqiang Li

IEEE Transactions on Multimedia, 23, 871–882 · 14 citations · arXiv