Zixiang Ai (艾子翔)


Ph.D. candidate

Supervisor: Prof. Jiahuan Zhou

Wangxuan Institute of Computer Technology, Peking University.

Beijing, China

E-mail: zxAi25@stu.pku.edu.cn


I am a Ph.D. candidate at the Wangxuan Institute of Computer Technology, School of Intelligence, Peking University, supervised by Prof. Jiahuan Zhou. I received my B.Eng. in Software Engineering from the College of Computer Science and Technology, Zhejiang University, in 2025. My research interests lie in 3D vision and graphics, with a focus on point cloud processing, scene understanding, and neural scene generation. I am particularly interested in developing efficient, geometry-aware models that unify perception and generation within a single framework. Ultimately, my goal is to build powerful real-world 3D perception models that seamlessly integrate understanding and generation capabilities, and can be deployed on humanoid robot platforms for intelligent interaction in complex environments. Previously, I was a research intern at the State Key Laboratory of CAD&CG, Zhejiang University, where I worked with Prof. Zhaopeng Cui on large-scale 3D scene reconstruction. These experiences have strengthened my passion for advancing both the theoretical foundations and practical applications of 3D visual understanding and generation.

 

Education

  • Intelligent Science and Technology, School of Intelligence, Peking University, 2025 - 2030(Expected)

  • Software Engineering, College of Computer Science, Zhejiang University, 2021 - 2025

 

Awards and Honors

  • Jinde Scholarship of Peking University, 2026

  • Peking University Merit Student, 2026

  • Outstanding Graduate of Zhejiang Province, 2025

  • Outstanding Graduate of Zhejiang University, 2025

  • China National Scholarship, 2024

  • First Class Scholarship of Zhejiang University, 2024

  • Second Class Scholarship of Zhejiang University, 2023

  • National First Prize of the 14th National Mathematics Competition for College Students

 

Research Interests

  • Point Cloud Prompt Learning

  • Parameter-Efficient Fine-Tuning

  • 3D Reconstruction

 

Publications

  1. (NeurIPS'26, Spotlight)-Zixiang Ai, Zhenyu Cui, Xu Zou, and Jiahuan Zhou*, "3R-Adapter: Retrieval, Rewiring, and Refinement for Efficient Adaptation of 3D Reconstruction Model", in Proceedings of the Fortieth Annual Conference on Neural Information Processing Systems, Sydney, Australia, Dec.6 - Dec.12, 2026
    [pdf]

  2. (TPAMI'26)-Zixiang Ai, Zhenyu Cui, Yufei Guo, Wenwen Qiang, Lei Chen, Jiwen Lu, and Jiahuan Zhou*, "GAPrompt++: Multi-Granular Geometry-Aware Point Cloud Prompt for 3D Vision Model", in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026
    [pdf] [code]

  3. (ICCV'25)-Zixiang Ai, Zhenyu Cui, Yuxin Peng, and Jiahuan Zhou*, "UPP: Unified Point-Level Prompting for Robust Point Cloud Analysis", in Proceedings of the International Conference on Computer Vision, pp.27359-27368, Honolulu, Hawai'i, USA, Oct.19 - Oct.23, 2025
    [pdf] [code] [中文解读] [我爱计算机视觉报道]

  4. (ICML'25)-Zixiang Ai, Zichen Liu, Yuanhang Lei, Zhenyu Cui, Xu Zou, and Jiahuan Zhou*, "GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model", in Proceedings of the International Conference on Machine Learning, Vancouver, Canada, Jul.13 - Jul.19, 2025
    [pdf] [code] [PaperWeekly报道]

  5. (ICML'25)-Zixiang Ai, Zichen Liu, and Jiahuan Zhou*, "Vision Graph Prompting via Semantic Low-Rank Decomposition", in Proceedings of the International Conference on Machine Learning, Vancouver, Canada, Jul.13 - Jul.19, 2025
    [pdf] [code] [PaperWeekly报道]

  6. (AAAI'25, Oral)-Zesong Yang, Jiale Shi, Ru Zhang, Zixiang Ai, Boming Zhao, Hujun Bao, Luwei Yang, and Zhaopeng Cui*, "GURecon: Learning Detailed 3D Geometric Uncertainties for Neural Surface Reconstruction", in Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, Philadelphia, Pennsylvania, USA, 2025

Note: * indicates the corresponding author; # indicates equal contribution.

 

Academic Service

Conference Reviewer:

  • International Conference on Machine Learning (ICML)

  • Conference on Neural Information Processing Systems (NeurIPS)

  • IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

  • European Conference on Computer Vision (ECCV)

  • International Conference on Learning Representations (ICLR)

  • AAAI Conference on Artificial Intelligence (AAAI)

Journal Reviewer: