Kaisiyuan Wang
I am currently an AI Research Scientist (Member of Technical Staff) at Alibaba Group (ATH), working on unified multimodal understanding and generation foundation models. I received my B.S. & M.S. degree from Harbin Institute of Technology, Electrical and Engineering School and Ph.D. degree from the University of Sydney, Electrical and Information Engineering School.
Before joining Alibaba, I was a Senior Research Scientist at Department of Computer Vision Technology (VIS), Baidu Inc., working closely with Hang Zhou and Ziwei Liu . My research focused on human-centric video generation and 3D vision, covering audio- and video-driven talking head synthesis, personalized portrait reenactment, co-speech gesture generation, and human-object interaction. Earlier, I worked with Wayne Wu , Qianyi Wu and Xinya Ji at Mobile Intelligence Group (MIG), SenseTime on emotional talking face generation.
Email  / 
CV  / 
Google Scholar  / 
Github
Research
My research interests include both human-centric (e.g., Human Video Synthesis and Co-speech Gesture Generation) and object-centric (e.g., Object-Compositional Implicit Scene Reconstruction) topics. Recently, I am pushing research in Human-Object Interaction (HOI) that can be applied in practical video generation techniques under digital human scenarios.
GestureHYDRA: Semantic Co-speech Gesture Synthesis via Hybrid Modality Diffusion Transformer and Cascaded Synchronized Retrieval-Augmented Generation
Quanwei Yang ,
Luying Huang ,
Kaisiyuan Wang †,
Jiazhi Guan ,
Shengyi He,
Fengguo Li,
Lingyun Yu,
Yingying Li,
Haocheng Feng,
Hang Zhou ,
Hongtao Xie †
ICCV 2025
project page
/
pdf
/
code
Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model
Yingying Fan,
Quanwei Yang ,
Kaisiyuan Wang †,
Hang Zhou ,
Yingying Li,
Haocheng Feng,
Errui Ding ,
Yu Wu †,
Jingdong Wang
CVPR 2025
project page
/
pdf
/
code
AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers
Jiazhi Guan ,
Kaisiyuan Wang ,
Zhiliang Xu,
Quanwei Yang ,
Yasheng Sun ,
Shengyi He,
Borong Liang,
Yingying Li,
Haocheng Feng,
Errui Ding ,
Jingdong Wang ,
Youjian Zhao †,
Hang Zhou †,
Ziwei Liu
CVPR 2025
project page
/
pdf
/
code
ShowMaker: Creating High-Fidelity 2D Human Video via Fine-Grained Diffusion Modeling
Quanwei Yang ,
Jiazhi Guan ,
Kaisiyuan Wang †,
Lingyun Yu ,
Wenqing Chu ,
Hang Zhou ,
Errui Ding ,
Jingdong Wang ,
Hongtao Xie †
NeurlPS 2024
project page
/
pdf
/
code
TALK-Act: Enhance Textural-Awareness for 2D Speaking Avatar Reenactment with Diffusion Model
Jiazhi Guan ,
Quanwei Yang,
Kaisiyuan Wang ,
Hang Zhou ,
Shengyi He,
Zhiliang Xu,
Haocheng Feng,
Errui Ding ,
Jingdong Wang ,
Hongtao Xie ,
Youjian Zhao ,
Ziwei Liu
Siggraph Asia 2024
project page
/
pdf
/
code
ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer
Jiazhi Guan ,
Zhiliang Xu,
Hang Zhou ,
Kaisiyuan Wang ,
Shengyi He,
Zhanwang Zhang,
Borong Liang,
Haocheng Feng,
Errui Ding ,
Jingtuo Liu ,
Jingdong Wang ,
Youjian Zhao ,
Ziwei Liu
ECCV 2024
project page
/
pdf
/
code
Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition
Jiaxiang Tang ,
Kaisiyuan Wang ,
Hang Zhou ,
Xiaokang Chen ,
Dongliang He ,
Tianshu Hu,
Jingtuo Liu ,
Gang Zeng ,
Jingdong Wang
Arxiv
project page
/
pdf
/
code
Objectsdf++: Improved Object-Compositional Neural Implicit Surfaces
Qianyi Wu ,
Kaisiyuan Wang ,
Kejie Li
Jianmin Zheng
Jianfei Cai
ICCV , 2023
project page
/
pdf
/
code
StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator
Jiazhi Guan,
Zhanwang Zhang,
Hang Zhou ,
Tianshu Hu,
Kaisiyuan Wang ,
Dongliang He ,
Haocheng Feng,
Jingtuo Liu ,
Errui Ding ,
Ziwei Liu ,
Jingdong Wang
CVPR , 2023
project page
/
pdf
/
code
Efficient Video Portrait Reenactment via Grid-based Codebook
Kaisiyuan Wang ,
Hang Zhou ,
Qianyi Wu ,
Jiaxiang Tang ,
Tianshu Hu,
Zhiliang Xu,
Borong Liang,
Tianshu Hu,
Errui Ding ,
Jingtuo Liu ,
Ziwei Liu ,
Jingdong Wang
Siggraph , 2023
project page
/
pdf
/
code
Robust Video Portrait Reenactment via Personalized Representation Quantization
Kaisiyuan Wang ,
Changcheng Liang,
Hang Zhou ,
Jiaxiang Tang ,
Qianyi Wu ,
Dongliang He ,
Zhibin Hong ,
Jingtuo Liu ,
Errui Ding ,
Ziwei Liu ,
Jingdong Wang
AAAI , 2023
project page
/
pdf
/
code
VPU: A Video-based Point cloud Upsampling framework
Kaisiyuan Wang ,
Lu Sheng ,
Shuhang Gu ,
Dong Xu ,
TIP , 2022
project page
/
pdf
/
code
Masked lip-sync prediction by audio-visual contextual exploitation in transformers
Yasheng Sun *,
Hang Zhou *,
Kaisiyuan Wang ,
Qianyi Wu ,
Zhibin Hong ,
Jingtuo Liu ,
Errui Ding ,
Jingdong Wang ,
Ziwei Liu ,
Koike Hideki
Siggraph Asia , 2022
project page
/
pdf
/
code
EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model
Xinya Ji,
Hang Zhou ,
Kaisiyuan Wang ,
Qianyi Wu ,
Wayne Wu ,
Feng Xu ,
Xun Cao
Siggraph , 2022
project page
/
pdf
/
code
Audio-Driven Emotional Video Portraits
Xinya Ji,
Hang Zhou ,
Kaisiyuan Wang ,
Qianyi Wu ,
Wayne Wu ,
Chen Change Loy ,
Xun Cao ,
Feng Xu
CVPR , 2021
project page
/
pdf
/
code
MEAD: A Large-scale Audio-visual Dataset for Emotional Talking-face Generation
Kaisiyuan Wang ,
Qianyi Wu ,
Linsen Song ,
Zhuoqian Yang ,
Wayne Wu ,
Chen Qian ,
Ran He ,
Yu Qiao ,
Chen Change Loy ,
ECCV , 2020
project page
/
pdf
/
code
Alibaba
AI Research Scientist, Member of Technical Staff
| ATH, Alibaba Group
May 2026 ~ Now
Unified multimodal understanding and generation foundation models
Senior Research Scientist
| VIS, Baidu Inc.
Beijing, China | 2024 ~ 2026
Personalized Video Portrait Reenactment
Person-agnostic Audio-driven Talking Head Synthesis
Research Intern for Digital Human, Feb. 2022 ~ 2024
Research Intern for Digital Human
| MIG, SenseTime
Beijing, China | Apr. 2019 ~ Jun. 2020
2D/3D Emotional Facial Expression Generation
Audio-driven Emotional Talking Head Synthesis
This website is adapted from Jon Barron's template.