Junkun Yuan 袁俊坤Research Scientist, Hunyuan Multimodal Generation Team @ Tencent yuanjk0921@outlook.com work and live in Shenzhen, China Last updated on July 06, 2025 at 23:05 (UTC+8) |
|
Biography
I am a research scientist in Hunyuan Multimodal Generation Team at Tencent, working on multimodal generative foundation models and their applications.
I previously worked/interned in Hunyuan Multimodal Generation Team at Tencent (working with Wei Liu) during Sep 2023 — Jul 2025, and in Computer Vision Group at Baidu (working with Xinyu Zhang and Jingdong Wang) during Jul 2022 — Aug 2023.
I received my PhD degree from Zhejiang University in 2024, co-supervised by professors of Kun Kuang, Lanfen Lin, and
Fei Wu.
Publications
Hunyuan-Game: Industrial-grade Intelligent Game Creation Model
Hunyuan Multimodal Generation Team at Tencent (as a team member)
May 20, 2025 | arXiv 2025 arXiv preprint
HunyuanVideo: A Systematic Framework For Large Video Generative Models
Hunyuan Multimodal Generation Team at Tencent (as a team member)
Dec 03, 2024 | code | arXiv 2024 arXiv preprint
It is an open-sourced large-scale video generation model with 13B parameters. It has 200+ citations and 10K+ GitHub stars (as of June 2025).
Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation
Qihua Chen✳, Yue Ma✳, Hongfa Wang✳, Junkun Yuan✳✉, Wenzhe Zhao, Qi Tian, Hongmei Wang, Shaobo Min, Qifeng Chen✉, and Wei Liu
Sep 02, 2024 | code | AAAI 2025 AAAI Conference on Artificial Intelligence
Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation
Yue Ma✳, Hongyu Liu✳, Hongfa Wang✳, Heng Pan✳, Yingqing He, Junkun Yuan, Ailing Zeng, Chengfei Cai, Heung-Yeung Shum, Wei Liu✉, and Qifeng Chen✉
Jun 04, 2024 | code | SIGGRAPH-Asia 2024 ACM SIGGRAPH Annual Conference in Asia
Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
Hunyuan Multimodal Generation Team at Tencent (as an intern)
May 14, 2024 | code | arXiv 2024 arXiv preprint
HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception
Junkun Yuan✳, Xinyu Zhang✳✉, Hao Zhou, Jian Wang, Zhongwei Qiu, Zhiyin Shao, Shaofeng Zhang, Sifan Long, Kun Kuang✉, Kun Yao, Junyu Han, Errui Ding, Lanfen Lin, Fei Wu, and Jingdong Wang✉
Oct 31, 2023 | code | NeurIPS 2023 Advances in Neural Information Processing Systems
MAP: Towards Balanced Generalization of IID and OOD through Model-Agnostic Adapters
Min Zhang, Junkun Yuan, Yue He, Wenbin Li, Zhengyu Chen, and Kun Kuang✉
Oct 02, 2023 | ICCV 2023 International Conference on Computer Vision
Neural Collapse Anchored Prompt Tuning for Generalizable Vision-Language Models
Didi Zhu, Zexi Li, Min Zhang, Junkun Yuan, Yunfeng Shao, Jiashuo Liu, Kun Kuang✉, Yinchuan Li, and Chao Wu
Jun 28, 2023 | KDD 2024 ACM SIGKDD Conference on Knowledge Discovery and Data Mining
Quantitatively Measuring and Contrastively Exploring Heterogeneity for Domain Generalization
Yunze Tong, Junkun Yuan, Min Zhang, Didi Zhu, Keli Zhang, Fei Wu, and Kun Kuang✉
May 25, 2023 | code | KDD 2023 ACM SIGKDD Conference on Knowledge Discovery and Data Mining
Universal Domain Adaptation via Compressive Attention Matching
Didi Zhu✳, Yincuan Li✳, Junkun Yuan, Zexi Li, Kun Kuang, and Chao Wu✉
Apr 24, 2023 | ICCV 2023 International Conference on Computer Vision
Mutual Prompt Leaning for Vision Language Models
Sifan Long✳, Zhen Zhao✳, Junkun Yuan✳, Zichang Tan✳, Jiangjiang Liu, Jingyuan Feng, Shengsheng Wang✉, and Jingdong Wang
Mar 30, 2023 | IJCV 2024 International Journal of Computer Vision
Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models
Sifan Long✳, Zhen Zhao✳, Junkun Yuan✳, Zichang Tan, Jiangjiang Liu, Luping Zhou, Shengsheng Wang✉, and Jingdong Wang✉
Mar 30, 2023 | ICCV 2023 International Conference on Computer Vision
CAE v2: Context Autoencoder with CLIP Target
Xinyu Zhang✳, Jiahui Chen✳, Junkun Yuan, Qiang Chen, Jian Wang, Xiaodi Wang, Shumin Han, Xiaokang Chen, Jimin Pi, Kun Yao, Junyu Han, Errui Ding, and Jingdong Wang✉
Nov 17, 2022 | code | TMLR 2023 Transactions on Machine Learning Research
Label-Efficient Domain Generalization via Collaborative Exploration and Generalization
Junkun Yuan✳, Xu Ma✳, Defang Chen, Kun Kuang✉, Fei Wu, and Lanfen Lin
Aug 07, 2022 | code | MM 2022 International Conference on Multimedia