Hengjia Li Ph.D. Candidate Computer Science and Technology Zhejiang University E-mail  /  CV  /  Google Scholar  /  LinkedIn

Biography

Hi, I'm Hengjia Li (李恒佳). I am currently a final-year Ph.D. student in the State Key Lab of CAD&CG at Zhejiang University guided by Pro. Deng Cai and Pro. Xiaofei He. Fortunatly, I am a visiting student at Human Sensing Lab, Carnegie Mellon University (CMU) guided by Pro. Fernando De La Torre. Before this, I received my bachelor's degree in Mathematical Sciences of Zhejiang University.

I have a broad interest in most areas of computer vision, especially in image/video generation and multi-modal understanding and reasoning with a recent focus on post training. Please do not hesitate to reach out to me via email at [email protected] !

News

• [06/2025] Three papers accepted by ICCV 2025.
• [01/2025] One paper accepted by ICLR 2025.
• [11/2024] Visit Human Sensing Lab of Carnegie Mellon University (CMU).
• [11/2024] One paper accepted by ICLR 2024.
• [12/2023] One paper accepted by AAAI 2024.

Selected Publications

* equal contribution

	ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing Hengjia Li, Liming Jiang, Qing Yan, Yizhi Song, Hao Kang, Zichuan Liu, Xin Lu, Boxi Wu, Deng Cai Under Review
	RULER-Bench: Probing Rule-based Reasoning Abilities of Next-level Video Generation Models for Vision Foundation Intelligence Xuming He*, Zehao Fan*, Hengjia Li*, Fan Zhuo, Hankun Xu, Senlin cheng, Di Weng, Haifeng Liu, Can Ye, Boxi Wu Under Review Project / arXiv
	MagicView: Multi-View Consistent Identity Customization via Priors-Guided In-Context Learning Hengjia Li, Jianjin Xu, Keli Cheng, Lei Wang, Ning Bi, Zheng Yang, Boxi Wu, Deng Cai, Fernando De la Torre Under Review arXiv
	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 International Conference on Computer Vision (ICCV), 2025 Project / arXiv / Code
	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 International Conference on Computer Vision (ICCV), 2025 Project / arXiv / Code
	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 International Conference on Learning Representations (ICLR), 2024 Project / arXiv / Code
	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 Under Review arXiv
	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 Under Review arXiv

Experiences

	Research Intern, Bytedance Seed Topic: Unified Multi-Modal Model Supervised by: Zihan Ding
	Research Intern, TikTok Topic: Reasoning-Centric Image Editing Supervised by: Liming Jiang
	Research Intern, Tongyi WanX Topic: Human-Centric Video Generation Supervised by: Shiwei Zhang
	Research Intern, HeyGen Topic: Multimodal Image Generation Supervised by: Yi Ren
	Research Intern, Hedra Topic: Human-Centric Video Generation Supervised by: Hongwei Yi
	Visiting Scholar, Human Sensing Lab, Carnegie Mellon University Topic: Human-Centric Image Generation Supervised by: Fernando De La Torre

Professional Services

• Conference Reviewer for CVPR (2025, 2026), ICLR(2025, 2026), ICCV (2025), NeurIPS (2024, 2025), ICML (2025), AAAI (2026), MM (2025), WACV (2025).
• Journal Reviewer for TIP