Junkun Yuan
Researcher
|
![]() |
I am a researcher of Hunyuan Foundation Model Team,
Tencent since 2024.07, working on visual generative foundation models.
My research interests include visual & multimodal foundation models and their various downstream applications.
During 2023.09 - 2024.06, I was an intern at Hunyuan Foundation Model Team,
Tencent, working with Wei Liu.
During 2022.07 - 2023.08, I was an intern at Baidu Computer Vision Group, working with Xinyu Zhang and Jingdong Wang.
I got Ph.D degree from Zhejiang University in 2024.06, supervised by Prof. Kun Kuang, Prof. Lanfen Lin, and Prof.
Fei Wu.
Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation
[2025.02, AAAI] AAAI Conference on Artificial IntelligenceHunyuanVideo: A Systematic Framework For Large Video Generative Models
[2024.12, Technical Report]Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation
[2024.12, SIGGRAPH-Asia] Computer Graphics and Interactive Techniques-AsiaMutual Prompt Leaning for Vision Language Models
[2024.09, IJCV] International Journal of Computer VisionNeural Collapse Anchored Prompt Tuning for Generalizable Vision-Language Models
[2024.08, KDD] ACM SIGKDD Conference on Knowledge Discovery and Data MiningHunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
[2024.05, Technical Report]Domaindiff: Boost out-of-Distribution Generalization with Synthetic Data
[2024.04, ICASSP] International Conference on Acoustics, Speech, and Signal ProcessingHAP: Structure-Aware Masked Image Modeling for Human-Centric Perception
[2023.12, NeurIPS] Advances in Neural Information Processing SystemsCollaborative Semantic Aggregation and Calibration for Federated Domain Generalization
[2023.12, TKDE] IEEE Transactions on Knowledge and Data EngineeringMAP: Towards Balanced Generalization of IID and OOD through Model-Agnostic Adapters
[2023.10, ICCV] International Conference on Computer VisionUniversal Domain Adaptation via Compressive Attention Matching
[2023.10, ICCV] International Conference on Computer VisionTask-Oriented Multi-Modal Mutual Leaning for Vision-Language Models
[2023.10, ICCV] International Conference on Computer VisionCAE v2: Context Autoencoder with CLIP Latent Alignment
[2023.09, TMLR] Transactions on Machine Learning ResearchQuantitatively Measuring and Contrastively Exploring Heterogeneity for Domain Generalization
[2023.08, KDD] ACM SIGKDD Conference on Knowledge Discovery and Data MiningInstrumental Variable-Driven Domain Generalization with Unobserved Confounders
[2023.06, TKDD] ACM Transactions on Knowledge Discovery from DataKnowledge Distillation-based Domain-invariant Representation Learning for Domain Generalization
[2023.04, TMM] IEEE Transactions on MultimediaDomain-Specific Bias Filtering for Single Labeled Domain Generalization
[2022.11, IJCV] International Journal of Computer VisionLabel-Efficient Domain Generalization via Collaborative Exploration and Generalization
[2022.10, MM] International Conference on MultimediaAttention-based Cross-Layer Domain Alignment for Unsupervised Domain Adaptation
[2022.08, Neurocomputing]Learning Decomposed Representations for Treatment Effect Estimation
[2022.02, TKDE] IEEE Transactions on Knowledge and Data EngineeringAuto IV: Counterfactual Prediction via Automatic Instrumental Variable Decomposition
[2022.01, TKDD] ACM Transactions on Knowledge Discovery from DataSubgraph Networks with Application to Structural Feature Space Expansion
[2021.12, TKDE] IEEE Transactions on Knowledge and Data EngineeringBlack-box Adversarial Attacks Against Deep Learning Based Malware Binaries Detection with GAN
[2020.08, ECAI] European Conference on Artificial IntelligenceCNN-based DGA Detection with High Coverage
[2019.07, ISI] International Conference on Intelligence and Security Informatics