About

Hi! I am Shaojie Zhang (张少杰). I am currently a research engineer at Xiaomi’s MiLM Plus Team. Before that, I have received my M.S. (2022-2025) and B.S. (2018-2022) degree in Beijing University of Posts and Telecommunications, advised by Prof. Jianqin Yin.

My research interests include Multi-modal Large Models, Multi-modal Reasoning, and Video Understanding.

News

Jul 01, 2026 🎉 The technical report of Xiaomi-GUI-0 has been released.
Jun 18, 2026 🎉 Two papers have been accepted by ECCV 2026.

Selected Publications

  1. arXiv
    cao2026xiaomigui.png
    Xiaomi-GUI-0 Technical Report
    Wanxia Cao, Chengzhen Duan, Pei Fu, and 29 more authors
    arXiv preprint arXiv:2606.31410, 2026
  2. ECCV
    lyu2026unitranslator.png
    UniTranslator: A Unified Multi-modal Framework for End-to-end In-Image Machine Translation
    J Lyu, P Fu, Z Li, and 6 more authors
    In European Conference on Computer Vision (ECCV), 2026
  3. ECCV
    wang2026gaia.png
    GAIA: A Data Flywheel System for Training GUI Test-Time Scaling Critic Models
    S Wang, P Fu, R Zhang, and 6 more authors
    In European Conference on Computer Vision (ECCV), 2026
  4. ICCV
    zhang2025qframe.png
    Q-Frame: Query-aware Frame Selection and Multi-resolution Adaptation for Video-LLMs
    Shaojie Zhang, J Yang, Jianqin Yin, and 2 more authors
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025
  5. NeurIPS
    zhang2025btlui.png
    BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent
    Shaojie Zhang, R Zhang, P Fu, and 6 more authors
    In Advances in Neural Information Processing Systems (NeurIPS), 2025
  6. PR
    zhang2025contrastive.png
    A Generically Contrastive Spatiotemporal Representation Enhancement for 3D Skeleton Action Recognition
    Shaojie Zhang, Jianqin Yin, and Yonghao Dang
    ELSEVIER Pattern Recognition (PR), 2025
  7. TCSVT
    zhang2024sitmlp.png
    SiT-MLP: A Simple MLP with Point-wise Topology Feature Learning for Skeleton-based Action Recognition
    Shaojie Zhang, Jianqin Yin, Yonghao Dang, and 1 more author
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024