I am a Researcher at Tencent HY, working with Heng Wang in the Video World Model Team. Previously, I worked with Qinglin Lu in the Video Application Team, and was a Research Intern at ByteDance Intelligent Creation Team, collaborating with Jie Wu and Pan Xie. I received my Master degree in Artificial Intelligence from Beihang University (2025).
I am currently exploring Video World Models. My research interests center on Diffusion Distillation and Preference Alignment. Welcome to discuss, feel free to reach out at jiaxiangcc@gmail.com.
🔥 News
- 2026.05: 🎉 One paper on human image animation accepted by ICML 2026.
- 2025.10: 🎉 One paper on video diffusion acceleration accepted by AAAI 2026.
- 2024.12: 🔥 Our HunyuanVideo is released, a systematic framework for large video generative models.
- 2024.11: 🏢 Joined
Tencent HY as Researcher. - 2024.11: 🎉 One paper ResAdapter accepted by AAAI 2025.
- 2023.04: 🏢 Joined
ByteDance Intelligent Creation as Research Intern.
📝 Recent Works
FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation
Yuanzhi Wang, Xuhua Ren, Jiaxiang Cheng, Bing Ma, Kai Yu, Sen Liang, Wenyue Li, Tianxiang Zheng, Qinglin Lu, Zhen Cui
- A pose-faithful approach for preserving facial identity in text-to-video generation.
📝 Publications
Implicit Preference Alignment for Human Image Animation CCF-A
Yuanzhi Wang, Xuhua Ren, Jiaxiang Cheng, Bing Ma, Kai Yu, Tianxiang Zheng, Qinglin Lu, Zhen Cui
- A preference alignment framework for human image animation that eliminates the need for paired preference data.
Phased One-step Adversarial Equilibrium for Video Diffusion Models CCF-A
Jiaxiang Cheng, Bing Ma, Xuhua Ren, Hongyi Henry Jin, Kai Yu, Peng Zhang, Wenyue Li, Yuan Zhou, Tianxiang Zheng, Qinglin Lu
- A novel phased adversarial training framework for one-step video generation with diffusion models.
ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models CCF-A
Jiaxiang Cheng, Pan Xie, Xin Xia, Jiashi Li, Jie Wu, Yuxi Ren, Huixia Li, Xuefeng Xiao, Min Zheng, Lean Fu
- A plug-and-play resolution adapter for diffusion models that enables arbitrary resolution generation without retraining.
- HunyuanVideo: A Systematic Framework for Large Video Generative Models, Weijie Kong, Qi Tian, Zijian Zhang, Rox Min, Zuozhuo Dai, …, Jiaxiang Cheng, et al., arXiv 2024 |
- 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, Jiaxiang Cheng, et al., arXiv 2025
- Beyond Reward Margin: Rethinking and Resolving Likelihood Displacement in Diffusion Models via Video Generation, Ruojun Xu, Yu Kai, Xuhua Ren, Jiaxiang Cheng, Bing Ma, Tianxiang Zheng, Qinglin Lu, arXiv 2025
- PersonaVlog: Personalized Multimodal Vlog Generation with Multi-Agent Collaboration and Iterative Self-Correction, Xiaolu Hou, Bing Ma, Jiaxiang Cheng, Xuhua Ren, Kai Yu, Wenyue Li, Tianxiang Zheng, Qinglin Lu, arXiv 2025
📖 Educations
- 2022.09 - 2025.06, M.S. in Artificial Intelligence, Beihang University, Beijing, China.
- 2018.09 - 2022.06, B.E. in Automation, Xidian University, Xi’an, China.
💻 Experience
- 2024.11 - Present, Researcher, Tencent HY, Beijing, China.
- 2023.04 - 2024.10, Research Intern, ByteDance Intelligent Creation, Beijing, China.