Xiaole Tang

Hello! I'm Xiaole Tang. I'm currently a fourth-year Ph.D. student in Mathematics at Xi'an Jiaotong University, advised by Prof. Jian Sun. I am also a visiting Ph.D. student in the group of Prof. Gabriele Steidl at TU Berlin (October 2026–March 2027).

Prior to that, I earned my B.S. degree at University of Electronic Science and Technology of China in 2023, advised by Prof. Xi-Le Zhao.

My research focuses on optimal transport and Wasserstein barycenters for multimodal representation learning and image restoration. I am also interested in multimodal generation and vision-language model post-training.

Portrait of Xiaole Tang

Education

2023–Present

Ph.D. in Mathematics

Xi'an Jiaotong University, China

Advisor: Prof. Jian Sun

2019–2023

B.S. in Applied Mathematics

University of Electronic Science and Technology of China

Advisor: Prof. Xi-Le Zhao

Research Interests

My research develops optimal transport and Wasserstein barycenter methods for multimodal representation learning and inverse problems. I study how distributional geometry can support scalable multimodal understanding and generation, unified image restoration, and robust generalization, with an emphasis on both mathematical foundations and practical validation.

Publications and Preprints

  1. Binding Multiple Modalities via Multimodal Wasserstein Barycenter

    Binding Multiple Modalities via Multimodal Wasserstein Barycenter

    Xiaole Tang, Jiayi Xu, Xiang Gu, Yan Yang, Jian Sun.

    NeurIPS 2026 (Oral).

    [Paper] [Code] [Project Page]

  2. Learning Continuous Wasserstein Barycenter Space

    Learning Continuous Wasserstein Barycenter Space for Generalized All-in-One Image Restoration

    Xiaole Tang, Xiaoyi He, Jiayi Xu, Xiang Gu, Jian Sun.

    IEEE TPAMI 2026.

    [Paper] [Code]

  3. Degradation-Aware Residual-Conditioned Optimal Transport

    Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration

    Xiaole Tang, Xiang Gu, Xiaoyi He, Xin Hu, Jian Sun.

    IEEE TPAMI 2025.

    [Paper] [Code]

  4. Residual-Conditioned Optimal Transport

    Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image Restoration

    Xiaole Tang, Xin Hu, Xiang Gu, Jian Sun.

    ICML 2024.

    [Paper] [Code]

  5. Uncertainty-Aware Unsupervised Image Deblurring

    Uncertainty-Aware Unsupervised Image Deblurring with Deep Residual Prior

    Xiaole Tang, Xi-Le Zhao, Jun Liu, Jian-Li Wang, Yuchun Miao, Tieyong Zeng.

    CVPR 2023.

    [Paper] [Code]

  6. Learning 3D Equivariant Implicit Function

    Learning 3D Equivariant Implicit Function with Patch-Level Pose-Invariant Representation

    Xin Hu, Xiaole Tang, Ruixuan Yu, Jian Sun.

    NeurIPS, 2024.

Honors and Projects

Academic Service