Rui Li - Homepage

About Me

Hello! I am Rui Li (李锐), a senior researcher at Tencent Hunyuan, where I work on the post-training of the HunyuanVideo foundation model. As a core contributor, I have been involved in the development and release of HunyuanVideo, and related multi-modal systems.

I received my Ph.D. in Information and Communication Engineering from the University of Science and Technology of China (USTC) in 2024, advised by Prof. Dong Liu in the VIDAR Lab.

My research centers on the analysis, representation, and generation of video. Recently I have been focusing mainly on video generative models.

Experience

Hunyuan

Researcher, Tencent Top Talent Program (青云计划)

2024.09 - Present

JD AI Research

Research Intern, Computer Vision Group (led by Tao Mei, now HiDream)

2020.10 - 2021.09

Publications

Published

TIP 2026LaCon: Late-Constraint Controllable Visual Generation

Chang Liu, Rui Li, Kaidong Zhang, Yunwei Lan, Xin Luo, Dong Liu

IEEE Transactions on Image Processing (TIP), 2026

Paper / arXiv / Code / Project
TCSVT 2025StableV2V: Stablizing Shape Consistency in Video-to-Video Editing

Chang Liu, Rui Li, Kaidong Zhang, Yunwei Lan, Dong Liu*

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025

Paper / arXiv / Code / Project
ECCV 2024Decomposition Betters Tracking Everything Everywhere

Rui Li, Dong Liu

European Conference on Computer Vision (ECCV), 2024

arXiv / Code
ICCV 2023Learning Fine-Grained Features for Pixel-wise Video Correspondences

Rui Li, Shenglong Zhou, Dong Liu

IEEE/CVF International Conference on Computer Vision (ICCV), 2023

Paper / arXiv / Code
CVPR 2023Spatial-Then-Temporal Self-Supervised Learning for Video Correspondence

Rui Li, Dong Liu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

Paper / arXiv / Code
ICCV 2021Motion-Focused Contrastive Learning of Video Representations

Rui Li, Yiheng Zhang, Zhaofan Qiu, Ting Yao, Dong Liu, Tao Mei

IEEE/CVF International Conference on Computer Vision (ICCV), 2021 (Oral, top 3%)

Paper / arXiv / Code
ACM MM 2019BERT4SessRec: Content-Based Video Relevance Prediction with Bidirectional Encoder Representations from Transformer

Xusong Chen, Dong Liu, Chenyi Lei, Rui Li, Zheng-Jun Zha, Zhiwei Xiong

ACM International Conference on Multimedia (MM), 2019

Paper

Technical Reports

HunyuanVideo 1.5 Technical Report

HunyuanVideo Foundation Team

Technical Report, 2025 · 4.5k+ GitHub stars

arXiv / Code
SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation

Rui Li*, Jiaming Zhang*, Shengming Cao*, Xiaotong Zhao, Yutao Cui, Xinglin Hou, Gangshan Wu, Haolan Chen, Yu Xu, Limin Wang, Kai Ma

arXiv preprint, 2025 · 600+ GitHub stars

arXiv / Code / Project
Latent Posterior-Mean Rectified Flow for Higher-Fidelity Perceptual Face Restoration

Xin Luo, Menglin Zhang, Yunwei Lan, Tianyu Zhang, Rui Li, Chang Liu, Dong Liu

arXiv preprint, 2025

arXiv / Code
NeRF Inpainting with Geometric Diffusion Prior and Balanced Score Distillation

Menglin Zhang, Xin Luo, Yunwei Lan, Chang Liu, Rui Li, Kaidong Zhang, Ganlin Yang, Dong Liu

arXiv preprint, 2024

arXiv

Awards

🥇

Champion, ACM Multimedia Video Relevance Prediction Challenge, 2019

🎓

Outstanding Graduate of Anhui Province, Anhui Provincial Department of Education, 2019

🏅

National Scholarship, Ministry of Education of China, 2018

🥉

Bronze Medal, National "Internet+" Innovation and Entrepreneurship Competition (Creative Group), 2018

🏆

Champion, Anhui "Internet+" Innovation and Entrepreneurship Competition (Creative Group), 2017

🥇

Gold Medal, Anhui "Chuang Qing Chun" Student Innovation Competition, 2017