avatar

Hengjia Li

Ph.D. Student
Zhejiang University
lihengjia98 (at) gmail.com


Hello 👋!

I am Hengjia Li, a Ph.D. student at State Key Lab of CAD&CG, Zhejiang University, advised by Prof. Deng Cai and Prof. Xiaofei He. Before that, I received my B.Eng. in Mathematical Sciences of Zhejiang University. And I am fortunate to be a research intern and collaborate with Liming Jiang at Tiktok, Shiwei Zhang at Tongyi WanX, Yi Ren at Heygen, and Hongwei Yi at Hedra. I also have the privilege of being a visiting scholar at Human Sensing Lab of Carnegie Mellon University (CMU), working under the guidance of Prof. Fernando De La Torre.

My research interests include multi-modal image and video generative models, with a recent focus on post training.

I am actively looking for a full-time research scientist position in industry starting from 2026. Please feel free to reach out if there is a good match.

News

Publications [Google Scholar]

(*) denotes equal contribution

  1. MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization
    Hengjia Li, Lifan Jiang, Xi Xiao, Tianyang Wang, Hongwei Yi, Boxi Wu, Deng Cai
    ICCV, 2025.
    Project Page arXiv Code GitHub stars

  2. PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation
    Hengjia Li, Haonan Qiu, Shiwei Zhang, Xiang Wang, Yujie Wei, Zekun Li, Yingya Zhang, Boxi Wu, Deng Cai
    ICCV, 2025.
    Project Page arXiv Code GitHub stars

  3. Few-shot Hybrid Domain Adaptation of Image Generators
    Hengjia Li, Yang Liu, Linxuan Xia, Yuqi Lin, Tu Zheng, Zheng Yang, Wenxiao Wang, Xiaohui Zhong, Xiaobo Ren, Xiaofei He
    ICLR, 2024.
    Project Page arXiv Code GitHub stars

  4. GCA-3D: Towards Generalized and Consistent Domain Adaptation of 3D Generators.
    Hengjia Li, Yang Liu, Yibo Zhao, Haoran Cheng, Yang Yang, Linxuan Xia, Zekai Luo, Qibo Qiu, Boxi Wu, Tu Zheng, Zheng Yang, Deng Cai
    arXiv, 2024.
    arXiv

  5. UniHDA: A Unified and Versatile Framework for Multi-Modal Hybrid Domain Adaptation
    Hengjia Li, Yang Liu, Yuqi Lin, Zhanwei Zhang, Yibo Zhao, weihang Pan, Tu Zheng, Zheng Yang, Yuchun Jiang, Boxi Wu, Deng Cai
    arxiv, 2024.
    Project Page arXiv

  6. DreamRelation: Relation-Centric Video Customization.
    Yujie Wei, Shiwei Zhang, Hangjie Yuan, Biao Gong, Longxiang Tang, Xiang Wang, Haonan Qiu, Hengjia Li, Shuai Tan, Yingya Zhang, Hongming Shan
    ICCV, 2025.
    Project Page arXiv

  7. Local Conditional Controlling for Text-to-Image Diffusion Models
    Yibo Zhao, Liang Peng, Yang Yang, Zekai Luo, Hengjia Li, Yao Chen, Wei Zhao, Wei Liu, Boxi Wu
    AAAI, 2025.
    arXiv Code GitHub stars

  8. Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection
    Zhanwei Zhang, Minghao Chen, Shuai Xiao, Liang Peng, Hengjia Li, Binbin Lin, Ping Li, Wenxiao Wang, Boxi Wu, Deng Cai
    CVPR, 2024.
    arXiv Code GitHub stars

  9. TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training
    Yuqi Lin, Minghao Chen, Kaipeng Zhang, Hengjia Li, Mingming Li, Zheng Yang, Dongqin Lv, Binbin Lin, Haifeng Liu, Deng Cai
    AAAI, 2024.
    arXiv Code GitHub stars

  10. APPT: Asymmetric Parallel Point Transformer for 3D Point Cloud Understanding
    Hengjia Li, Tu Zheng, Zhihao Chi, Zheng Yang, Wenxiao Wang, Boxi Wu, Binbin Lin, Deng Cai
    arXiv, 2023.
    arXiv

  11. NormKD: Normalized Logits for Knowledge Distillation
    Zhihao Chi, Tu Zheng, Hengjia Li, Zheng Yang, Boxi Wu, Binbin Lin, Deng Cai
    arXiv, 2023.
    arXiv

Services

Conference Reviewers


© Hengjia, 2023