I am a senior researcher specializing in Generative AI at Tencent Youtu Lab. Previously, I worked as a full-time engineer at Kwai from 2021 to 2023. I also completed research internships at Kwai (mentored by Haibin Huang and Chongyang Ma) and Tencent AI Lab. I obtained my Bachelor’s and Master’s (supervised by Prof. Nong Sang) degrees from Huazhong University of Science and Technology (HUST) in 2018 and 2021, respectively.

News

  • Awarded 2nd Place (“XuanYuan” on Leaderboard) in ACM MM Identity-Preserving Video Generation (IPVG) Challenge, 2025.

Publications

From Large Angles to Consistent Faces: Identity-Preserving Video Generation via Mixture of Facial Experts
From Large Angles to Consistent Faces: Identity-Preserving Video Generation via Mixture of Facial Experts [paper]
Yuji Wang*, Moran Li*, Xiaobin Hu*, Ran Yi, Jiangning Zhang, Chengming Xu, Weijian Cao, Yabiao Wang, Chengjie Wang, Lizhuang Ma
arxiv, 2025
Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations
Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations [paper] [code]
Yuji Wang*, Moran Li*, Xiaobin Hu*, Ran Yi, Jiangning Zhang, Han Feng, Weijian Cao, Yabiao Wang, Chengjie Wang, Lizhuang Ma
ACM International Conference on Multimedia (ACM MM), 2025 [CCF A]
StrandDesigner: Towards Practical Strand Generation with Sketch Guidance
StrandDesigner: Towards Practical Strand Generation with Sketch Guidance [paper] [code]
Na Zhang*, Moran Li*, Chengming Xu, Han Feng, Xiaobin Hu, Jiangning Zhang, Weijian Cao, Chengjie Wang, Yanwei Fu
ACM International Conference on Multimedia (ACM MM), 2025 [CCF A]
ID-Sculpt: ID-aware 3D Head Generation from Single In-the-wild Portrait Image
ID-Sculpt: ID-aware 3D Head Generation from Single In-the-wild Portrait Image [project] [paper]
Jinkun Hao, Junshu Tang, Jiangning Zhang, Ran Yi, Yijia Hong, Moran Li, Weijian Cao, Yating Wang, Chengjie Wang, Lizhuang Ma
AAAI Conference on Artificial Intelligence (AAAI), 2025 [CCF A]
FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis
FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis [project] [paper] [code]
Ke Fan, Junshu Tang, Weijian Cao, Ran Yi, Moran Li, Jingyu Gong, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Lizhuang Ma
European Conference on Computer Vision (ECCV), 2024 [CCF B]
DMTG: One-Shot Differentiable Multi-Task Grouping
DMTG: One-Shot Differentiable Multi-Task Grouping [paper] [code]
Yuan Gao, Shuguo Jiang, Moran Li, Jin-Gang Yu, Gui-Song Xia
International Conference on Machine Learning (ICML), 2024 [CCF A]
HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling
HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling [project] [paper] [code]
Yujian Zheng, Zirong Jin, Moran Li, Haibin Huang, Chongyang Ma, Shuguang Cui, Xiaoguang Han
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023 [CCF A]
Implicit Neural Deformation for Sparse‐View Face Reconstruction
Implicit Neural Deformation for Sparse-View Face Reconstruction [paper]
Moran Li, Haibin Huang, Yi Zheng, Mengtian Li, Nong Sang, Chongyang Ma
Pacific Graphics 2022 (PG), 2022 [CCF B]
Exploiting Learnable Joint Groups for Hand Pose Estimation
Exploiting Learnable Joint Groups for Hand Pose Estimation [paper] [code]
Moran Li, Yuan Gao, Nong Sang
AAAI Conference on Artificial Intelligence (AAAI), 2021 [CCF A]
Latent Distribution-Based 3D Hand Pose Estimation From Monocular RGB Images
Latent Distribution-Based 3D Hand Pose Estimation From Monocular RGB Images [paper]
Moran Li, Jialong Wang, Nong Sang
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2021 [CCF B]

Honors & Awards

  • Outstanding Graduate, 2018/2021
  • National Scholarship (top 2%), 2017

Education

  • 2018.09 ~ 2021.07, HUST, AIA Dept, Master
  • 2014.09 ~ 2018.07, HUST, OEI Dept and Qiming College, Bachelor