Junkun Yuan   袁俊坤

Research Scientist,  Hunyuan Multimodal Model Group  @  Tencent

yuanjk0921@outlook.com

work and live in Shenzhen, China

Last updated on September 06, 2025 at 12:44 (UTC+8)

I am currently on the job market and welcome potential opportunities. Please feel free to reach out to me.

Biography

I have been working as a research scientist in the Foundation Model Team of the Hunyuan Multimodal Model Group at Tencent since Jul 2024, working with Zhao Zhong and Liefeng Bo. I am focusing on multimodal generative foundation models and their various downstream applications.

During Sep 2023 — Jul 2024, I interned in the Hunyuan Multimodal Model Group at Tencent, working with Wei Liu. During Jul 2022 — Aug 2023, I interned in the Computer Vision Group at Baidu, working with Xinyu Zhang and Jingdong Wang.

I received my Ph.D. degree in Computer Science from Zhejiang University (2019 — 2024), co-supervised by professors of Kun Kuang, Lanfen Lin, and Fei Wu. I received my B.S. degree in Automation from Zhejiang University of Technology (2015 — 2019), co-supervised by professors of Qi Xuan and Li Yu.

I have been fortunate to work closely with some friends such as Defang Chen and Yue Ma, their insights also profoundly shape my approach to research.

Publications

Google Scholar Profile

Hunyuan-Game (arXiv 2025) HunyuanVideo (arXiv 2024) Follow-Your-Canvas (AAAI 2025) Follow-Your-Emoji (SIGGRAPH-Asia 2024) Domaindiff (ICASSP 2024) KDDRL (TMM 2023) HAP (NeurIPS 2023) MAP (ICCV 2023) NPT (KDD 2024) HTCL (KDD 2023) CAM (ICCV 2023) MPL (IJCV 2024) MPL (ICCV 2023) CAE v2 (TMLR 2023) CEG (MM 2022) ACDA (Neurocomputing 2022) DSBF (IJCV 2022) CSAC (TKDE 2023) DSBF (TKDD 2023) AutoIV (TKDD 2022) GAPGAN (ECAI 2020) DeR-CFR (TKDE 2023) SGNs (TKDE 2021)

Hunyuan-Game: Industrial-grade Intelligent Game Creation Model

Hunyuan Multimodal Model Group at Tencent (as a group member)

arXiv preprint (arXiv), 2025

May 20, 2025   |   Hunyuan-Game

paper   |   code

HunyuanVideo: A Systematic Framework For Large Video Generative Models

Hunyuan Multimodal Model Group at Tencent (as a group member)

arXiv preprint (arXiv), 2024

Dec 03, 2024   |   HunyuanVideo

paper   |   code

It is an open-source large-scale video generation model with 13B parameters. It has over 300 citations and over 10,000 GitHub stars (as of Aug 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

AAAI Conference on Artificial Intelligence (AAAI), 2025

Sep 02, 2024   |   Follow-Your-Canvas

paper   |   code

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

ACM SIGGRAPH Annual Conference in Asia (SIGGRAPH-Asia), 2024

Jun 04, 2024   |   Follow-Your-Emoji

paper   |   code

Domaindiff: Boost Out-of-Distribution Generalization with Synthetic Data

Qiaowei Miao, Junkun Yuan, Shengyu Zhang, Fei Wu, and Kun Kuang

International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024

Apr 14, 2024   |   Domaindiff

paper

Knowledge Distillation-Based Domain-Invariant Representation Learning for Domain Generalization

Ziwei Niu, Junkun Yuan, Xu Ma, Yingying Xu, Jing Liu, Yen-Wei Chen, Ruofeng Tong, and Lanfen Lin

IEEE Transactions on Multimedia (TMM), 2023

Jan 01, 2024   |   KDDRL

paper

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, and Kun Kuang, Kun Yao, Junyu Han, Errui Ding, Lanfen Lin, Fei Wu, and Jingdong Wang

Advances in Neural Information Processing Systems (NeurIPS), 2023

Oct 31, 2023   |   HAP

paper   |   code

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

International Conference on Computer Vision (ICCV), 2023

Oct 02, 2023   |   MAP

paper   |   code

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

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024

Jun 28, 2023   |   NPT

paper

Quantitatively Measuring and Contrastively Exploring Heterogeneity for Domain Generalization

Yunze Tong, Junkun Yuan, Min Zhang, Didi Zhu, Keli Zhang, Fei Wu, and Kun Kuang

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023

May 25, 2023   |   HTCL

paper   |   code

Universal Domain Adaptation via Compressive Attention Matching

Didi Zhu, Yincuan Li, Junkun Yuan, Zexi Li, Kun Kuang, and Chao Wu

International Conference on Computer Vision (ICCV), 2023

Apr 24, 2023   |   CAM

paper

Mutual Prompt Learning for Vision Language Models

Sifan Long, Zhen Zhao, Junkun Yuan, Zichang Tan, Jiangjiang Liu, Jingyuan Feng, Shengsheng Wang, and Jingdong Wang

International Journal of Computer Vision (IJCV), 2024

Mar 30, 2023   |   MPL

paper

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

International Conference on Computer Vision (ICCV), 2023

Mar 30, 2023   |   MPL

paper

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

Transactions on Machine Learning Research (TMLR), 2023

Nov 17, 2022   |   CAE v2

paper   |   code

Label-Efficient Domain Generalization via Collaborative Exploration and Generalization

Junkun Yuan, Xu Ma, Defang Chen, Kun Kuang, Fei Wu, and Lanfen Lin

International Conference on Multimedia (MM), 2022

Aug 07, 2022   |   CEG

paper   |   code

Attention-based Cross-Layer Domain Alignment for Unsupervised Domain Adaptation

Xu Ma, Junkun Yuan, Yen-Wei Chen, Ruofeng Tong, and Lanfen Lin

(Neurocomputing), 2022

Feb 27, 2022   |   ACDA

paper

Domain-Specific Bias Filtering for Single Labeled Domain Generalization

Junkun Yuan, Xu Ma, Defang Chen, Kun Kuang, Fei Wu, and Lanfen Lin

International Journal of Computer Vision (IJCV), 2022

Oct 02, 2021   |   DSBF

paper   |   code

Collaborative Semantic Aggregation and Calibration for Federated Domain Generalization

Junkun Yuan, Xu Ma, Defang Chen, Fei Wu, Lanfen Lin, and Kun Kuang

IEEE Transactions on Knowledge and Data Engineering (TKDE), 2023

Oct 13, 2021   |   CSAC

paper   |   code

Instrumental Variable-Driven Domain Generalization with Unobserved Confounders

Junkun Yuan, Xu Ma, Kun Kuang, Ruoxuan Xiong, Mingming Gong, and Lanfen Lin

ACM Transactions on Knowledge Discovery from Data (TKDD), 2023

Oct 04, 2021   |   DSBF

paper   |   code

Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decomposition

Junkun Yuan, Anpeng Wu, Kun Kuang, Bo Li, Runze Wu, Fei Wu, and Lanfen Lin

ACM Transactions on Knowledge Discovery from Data (TKDD), 2022

Jul 13, 2021   |   AutoIV

paper   |   code

Black-Box Adversarial Attacks Against Deep Learning Based Malware Binaries Detection with GAN

Junkun Yuan, Shaofang Zhou, Lanfen Lin, Feng Wang, and Jia Cui

European Conference on Artificial Intelligence (ECAI), 2020

Aug 29, 2020   |   GAPGAN

paper

Learning Decomposed Representation for Counterfactual Inference

Anpeng Wu, Junkun Yuan, Kun Kuang, Bo Li, Runze Wu, Qiang Zhu, Yueting Zhuang, and Fei Wu

IEEE Transactions on Knowledge and Data Engineering (TKDE), 2023

Jun 12, 2020   |   DeR-CFR

paper   |   code

Subgraph Networks with Application to Structural Feature Space Expansion

Qi Xuan, Jinhuan Wang, Minghao Zhao, Junkun Yuan, Chenbo Fu, Zhongyuan Ruan, Guanrong Chen

IEEE Transactions on Knowledge and Data Engineering (TKDE), 2021

Mar 21, 2019   |   SGNs

paper   |   code


Professional Service