banner

Biography 简介

Zejian Li is an Platform Top 100 Researcher with School of Software Technology, Zhejiang University, China. He is a member of International Design Institue, working closely with Prof. Lingyun Sun. He received his Ph.D. degree from Zhejiang University, China, in 2019. His Ph.D advisor is Prof. Yongchuan Tang. His research interests include generative models and intelligent design.

李泽健是浙江大学软件学院平台“百人计划”研究员，浙江大学国际设计研究院孙凌云教授团队成员。2019年在浙江大学获得计算机科学与技术博士学位，导师是汤永川教授。研究方向主要为生成模型和智能设计。

Research Interests 研究兴趣

Generative Models, intelligent design 生成模型，智能设计

Specific research interests:

  • Controllable Image/3D/4D generation
  • Training and Distillation of Diffusion Models
  • Evaluation of Generative Content
  • Interative Human-AI Cocreation

具体研究焦点：

  • 可控 图像/3D/4D 内容生成
  • 扩散模型训练和蒸馏
  • 生成内容质量评估
  • 交互式人机协同创作

Openings / Internship 招募和实习

I am looking for self-motivated PhD, master and undergraduate students to join my research group! I am also looking for postdoc and research assistant. If you are interested in generative models, Human-AI cocreation and want to join us, please send me your CV to zejianlee at zju.edu.cn. For those who are pursuing master degrees, notice that right now I only have master quota of industrial design engineering, but not software engineering or artificial intelligence.

团队招收博士生、硕士生和对科研感兴趣的本科生，以及博士后和研究助理。代表性作品包括人工智能发展简史图谱、《运河·生长·万象》系列作品、“墨染”系列国画创作系统和若干生成算法成果。代表性课程是《智能设计》（研究生课程）。如果你对生成模型、人机协同创作的研究感兴趣，有意向加入我们团队，欢迎发邮件到zejianlee at zju.edu.cn，请附个人简历。因为我隶属设计学科，硕士名额暂时只有“工业设计工程”专业，（虽然我也有人工智能、软件工程的招生资格），如果联系读研请说明是否接受工业设计工程的名额。团队内往届工业设计工程专业的硕士生，技术背景的小同学从事生成算法研究，设计背景的小同学从事人机协作方向研究，组内相互合作搞点大招。

Professional Activities 学术活动

Reviewer for ICLR, NeurIPS, CVPR, ICCV, ECCV, AAAI, etc.

ICLR, NeurIPS, CVPR, ICCV, ECCV, AAAI 等AI顶会的审稿人。

News 最新动态

  • [2024-03-09]
    Our online course on Large Model is released on https://www.xueyinonline.com/detail/250928740. 由孙凌云教授和我联合主讲的课程“人工智能大模型前沿与应用”已经在 https://www.xueyinonline.com/detail/250928740。后续会逐步更新增补新内容。

  • [2024-05-29]
    I give a lecture for the course “The Introduction of AI Large Models for Everyone (Designers)” on the basic principles of AIGC algorithms. The playback can be found in the video posts of “Zheda Design”.
    在浙江大学通识课“面向每个人（设计师）的AI大模型课”上讲授第五讲“AIGC基本原理”。回放可以在“浙大设计”微信视频号中观看。
  • [2024-05-15]
    I give a lecture for the course “The Introduction of AI Large Models for Everyone (Designers)” on selected topics of data, algorithms and computation power. The playback can be found in the video posts of “Zheda Design”.
    在浙江大学通识课“面向每个人（设计师）的AI大模型课”上讲授第三讲“数据、算法和算力”。回放可以在“浙大设计”微信视频号中观看。

Selected Publications 部分发表内容

  • Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion.
    Shengyuan Zhang, An Zhao, Ling Yang, Zejian Li, Chenye Meng, Haoran Xu, Tianrun Chen, AnYang Wei, Perry Pengyun GU, Lingyun Sun.
    https://arxiv.org/abs/2412.03515

  • Img2CAD: Conditioned 3D CAD Model Generation from Single Image with Structured Visual Geometry.
    Tianrun Chen, Chunan Yu, Yuanqi Hu, Jing Li, Tao Xu, Runlong Cao, Lanyun Zhu, Ying Zang, Yong Zhang, Zejian Li, Linyun Sun.
    https://arxiv.org/abs/2410.03417

  • Let Human Sketches Help: Empowering Challenging Image Segmentation Task with Freehand Sketches.
    Ying Zang, Runlong Cao, Jianqi Zhang, Yidong Han, Ziyue Cao, Wenjun Hu, Didi Zhu, Lanyun Zhu, Zejian Li, Deyi Ji, Tianrun Chen.
    https://arxiv.org/abs/2501.19329

  • Syllables to Scenes: Literary-Guided Free-Viewpoint 3D Scene Synthesis from Japanese Haiku
    Chunan Yu, Yidong Han, Chaotao Ding, Ying Zang, Lanyun Zhu, Xinhao Chen, Zejian Li, Renjun Xu, Tianrun Chen.
    https://arxiv.org/abs/2502.11586

  • LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations.
    Zejian Li, Chenye Meng, Yize Li, Ling Yang, Shengyuan Zhang, Jiarui Ma, Jiayi Li, Guang Yang, Changyuan Yang, Zhiyuan Yang, Jinxiong Chang, Lingyun Sun.
    https://arxiv.org/abs/2412.08580

  • Ink-Restorer: Virtual Restoration of Ancient Chinese Paintings Inheriting Traditional Restoration Processe.
    Ying Zhang, Zejian Li*, Jiesi Zhang, Fang Hu, Kewen Zhu, Liu Qi, Huanghuang Deng, Xiaoyu Chen, Lingyun Sun.
    ACM Conference on Human Factors in Computing Systems, 2025. CCF-A.

  • FusionProtor: A Mixed-Prototype Tool for Component-level Physical-to-Virtual 3D Transition and Simulation.
    Hongbo ZHANG, Pei Chen, Xuelong Xie, Zhaoqu Jiang, Yifei Wu, Zejian Li, Xiaoyu Chen, Lingyun Sun.
    ACM Conference on Human Factors in Computing Systems, 2025. CCF-A.

  • CharacterCritique: Supporting Children’s Development of Critical Thinking through Multi-Agent Interaction in Story Reading.
    Zizhen Wang, Jiangyu Pan, Duola Jin, Jingao Zhang, Jiacheng Cao, Chao Zhang, Zejian Li, Preben Hansen, Yijun Zhao, Shouqian Sun, Xianyue Qiao.
    ACM Conference on Human Factors in Computing Systems, 2025. CCF-A.

  • Image Generation Evaluation: A Comprehensive Survey of Human and Automatic Evaluation.
    Qi Liu, Shuanglin Yang, ZeJian Li*, Lefan Hou, Chenye Meng, Ying Zhang, Lingyun Sun.
    Frontiers of Information Technology & Electronic Engineering, 2025. CCF-C

  • Distribution Backtracking Builds A Faster Convergence Trajectory for Diffusion Distillation.
    Shengyuan Zhang, Ling Yang, Zejian Li*, An Zhao, Chenye Meng, Changyuan Yang, Guang Yang, Zhiyuan Yang, Lingyun Sun
    International Conference of Representation Learning, 2025. THU-A

  • Deep3DSketch-im: rapid high-fidelity AI 3D model generation by single freehand sketches.
    Tianrun Chen, Runlong Cao, Zejian Li, Ying Zang, Lingyun Sun.
    Frontiers of Information Technology & Electronic Engineering, 2024. CCF-C

  • Reality3dsketch: Rapid 3d modeling of objects from single freehand sketches.
    Tianrun Chen, Chaotao Ding, Lanyun Zhu, Ying Zang, Yiyi Liao, Zejian Li, Ling Sun.
    IEEE Transactions on Multimedia. 2024. CCF-B

  • RealtimeGen: An Intervenable AI Image Generation System for Commercial Digital Art Asset Creators.
    Zejian Li, Ying Zhang, Shengzhe Zhou, Qi Liu, Jiesi Zhang, Haoran Xu, Shuyao Chen, Xiaoyu Chen, Lingyun Sun.
    *International Journal of Human–Computer Interaction    , 2024. CCF-B paper

  • Rapid 3D Model Generation with Intuitive 3D Input.
    Tianrun Chen, Chaotao Ding, Shangzhan Zhang, Chunan Yu, Ying Zang*, Zejian Li*, Sida Peng, Lingyun Sun.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. CCF-A paper

  • Reducing Spatial Fitting Error in Distillation of Denoising Diffusion Models.
    Shengzhe Zhou, Zejian Li*, Shengyuan Zhang, Lefan Hou, Changyuan Yang, Guang Yang, Zhiyuan Yang, Lingyun Sun.
    AAAI Conference on Artificial Intelligence, 2024. CCF-A paper

  • SAM Fails to Segment Anything? - SAM-Adapter: Adapting SAM in Underperformed Scenes: Camouflage, Shadow, and More.
    Tianrun Chen, Lanyun Zhu, Chao Ding, Runlong Cao, Shangzhan Zhang, Yan Wang, Zejian Li, Lingyun Sun, Papa Mao, Ying-Dong Zang
    IEEE International Conference on Computer Vision Workshop, 2023. project paper

  • Learning Object Consistency and Interaction in Image Generation from Scene Graphs.
    Yangkang Zhang, Chenye Meng, Zejian Li*, Pei Chen, Guang Yang, Changyuan Yang, Lingyun Sun.
    International Joint Conference on Artificial Intelligence (IJCAI), 2023. CCF-A paper

  • UI Layers Merger: Merging UI Layers via Visual Learning and Boundary Prior.
    Yun-nong Chen, Yan-kun Zhen, Chu-ning Shi, Jia-zhi Li, Liu-qing Chen, Ze-jian Li, Ling-yun Sun, Ting-ting Zhou, Yan-fang Chang.
    Frontiers of Information Technology & Electronic Engineering (FITEE), 2022. CCF-C

  • Magical Brush: A Symbol-Based Modern Chinese Painting System for Novices.
    Haoran Xu, Shuyao Chen, Ying Zhang.
    ACM CHI Conference on Human Factors in Computing Systems, 2023. CCF-A

  • USIS: A unified semantic image synthesis model trained on a single or multiple samples.
    Pei Chen, Zejian Li*, Yangkang Zhang, Yongchuan Tang, Lingyun Sun.
    Neurocomputing, 2022. CCF-C

  • Preserving Structural Consistency in Arbitrary Artist and Artwork Style Transfer.
    Jingyu Wu, Lefan Hou, Zejian Li*, Jun Liao, Li Liu, Lingyun Sun.
    AAAI Conference on Artificial Intelligence, 2023. CCF-A

  • Recognizing Cognitive Load by a Hybrid Spatio-Temporal Causal Model from Multivariate Physiological Data.
    Zirui Yong, Li Liu, Guoxin Su, Xiaohu Li, Lingyun Sun, Zejian Li.
    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases ,2022, CCF-B

  • Few-Shot Incremental Learning for Label-to-Image Translation.
    Pei Chen, Yangkang Zhang, Zejian Li*, Lingyun Sun.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022. CCF-A

  • Image Synthesis from Layout with Locality-Aware Mask Adaption.
    Zejian Li, Jingyu Wu, Immanuel Koh, Yongchuan Tang and Lingyun Sun.
    *IEEE International Conference on Computer Vision    , 2021. CCF-A

  • FET-GAN: Font and Effect Transfer via K-shot Adaptive Instance Normalization.
    Wei Li, Yongxing He, Yanwei Qi, Zejian Li and Yongchuan Tang.
    *AAAI Conference on Artificial Intelligence    , 2020. CCF-A

  • A review of design intelligence: progress, problems, and challenges.
    Yongchuan Tang*, Jiangjie Huang, Mengting Yao, Jia Wei, Wei Li, Yongxing He, Zejian Li.
    Frontiers of Information Technology & Electronic Engineering, 2020. CCF-C

  • Learning Disentangled Representation with Pairwise Independence.
    Zejian Li, Yongchuan Tang*, Wei Li and Yongxing He.
    AAAI Conference on Artificial Intelligence, 2019. CCF-A

  • Unsupervised Disentangled Representation Learning with Analogical Relations.
    Zejian Li, Yongchuan Tang*, and Yongxing He.
    International Joint Conference on Artificial Intelligence, 2018. CCF-A

拉到最下的你，不管是拖下来还是翻下来的，都非常感谢你看到这里。如果还想更多了解我们团队的情（ba）况（gua），可以关注我们小同学的小红书。