Leyi Wu

Undergraduate student in Artificial Intelligence, HKUST(GZ)

prof_pic.jpg

HKUST(GZ)

Guangzhou, Shenzhen

lwu398@connect.hkust-gz.edu.cn

I am a fourth-year undergraduate student at The Hong Kong University of Science and Technology (Guangzhou), majoring in Artificial Intelligence. I am a member of EnVision Lab, where I work closely with Dongyu Yan, Tianshuo Xu, and Zhifei Chen, under the guidance of Prof. Ying-Cong Chen.

My research interests center on VLM reasoning, embodied AI, and generative models for video and 3D. I am especially interested in robust visual reasoning under imperfect real-world conditions, controllable video generation, and embodied systems that remain reliable under dynamic visual interference.

Recently, I won both tracks of the 1st Cross-Domain EgoCross Challenge @ EgoVis, CVPR 2026, and was awarded the 2025 China National Scholarship and the Litchi Innovation Talent Scholarship.

news

Oct 21, 2026 Two papers, Seg3DParts and Motion Forcing, have been accepted to NeurIPS 2026.
Jun 20, 2026 Our paper STANCE: Motion Coherent Video Generation Via Sparse-to-Dense Anchored Encoding was accepted to ECCV 2026.
Jun 04, 2026 We won both the Source-Limited Track and Open-Source Track of the 1st Cross-Domain EgoCross Challenge under the third EgoVis Workshop at CVPR 2026.
Jun 02, 2026 We released RoboStressBench, a benchmark for evaluating VLM robustness to physical visual stress in embodied scenes.
Jan 26, 2026 Our paper UniCalli was accepted to ICLR 2026.
Nov 01, 2025 I received the 2025 China National Scholarship, with one quota in the entire school.
Oct 16, 2025 We released STANCE, a sparse-to-dense anchored encoding framework for motion-coherent video generation.
Jun 03, 2025 We released FlexPainter, a flexible and multi-view consistent texture generation method.

selected publications

  1. NeurIPS2026
    Seg3DParts: Segmentation-Grounded Controllable Part-Level 3D Generation
    Jiantao Lin*, Meixi Chen*, Yingjie Xu*, Chenbo Fu, Leyi Wu, Hao Chen, Yinchuan Li, and Ying-Cong Chen
    In NeurIPS 2026, 2026
    arXiv HTML PDF
  2. Under Review
    Anvil: Scaling Embodied Spatial Intelligence through Knowledge Recirculation
    Weilin Ruan, Bohan Zhou, Jinghao Li, Yangkai Wei, Wenqian Li, Peiran Dong, Yingjie Xu, Leyi Wu, Haojian Huang, Binghui Xie, Han Yang, Kaiwen Zhou, Yinchuan Li, Ying-Cong Chen, and James Cheng
    Under Review, 2026
    arXiv HTML PDF
  3. Under Review
    robostressbench.png
    RoboStressBench: Benchmarking VLM Robustness to Physical Visual Stress in Embodied Scenes
    Leyi Wu*, Yifan Zhao*, Jinjie Zhang*, Suzeyu Chen*, Wosong Chen, Zhifei Chen, Tianshuo Xu, Qingchun He, Hongxin Hu, Haojian Huang, Yangkai Wei, Wenqian Li, Yinchuan Li, and Ying-Cong Chen†
    Under Review, 2026
    arXiv HTML PDF Website
  4. ECCV2026
    stance.png
    STANCE: Motion Coherent Video Generation Via Sparse-to-Dense Anchored Encoding
    Zhifei Chen*, Tianshuo Xu*, Leyi Wu*, Luozhou Wang, Dongyu Yan, Zihan You, Wenting Luo, Guo Zhang, and Yingcong Chen†
    In ECCV 2026, 2026
    PDF Code Website
  5. ICLR2026
    unicalli.png
    UniCalli: A Unified Diffusion Framework for Column-Level Generation and Recognition of Chinese Calligraphy
    Tianshuo Xu, Kai Wang, Zhifei Chen, Leyi Wu, Tianshui Wen, Fei Chao, and Ying-Cong Chen†
    In ICLR 2026, 2026
    PDF Code Website
  6. Under Review
    animationbench.png
    AnimationBench: Are Video Models Good at Character-Centric Animation?
    Leyi Wu*, Pengjun Fang*, Kai Sun*, Yazhou Xing†, Yinwei Wu, Songsong Wang, Ziqi Huang, Dan Zhou, Yingqing He, Ying-Cong Chen, and Qifeng Chen†
    2026
    arXiv PDF Website
  7. NeurIPS2026
    motion_forcing.png
    Motion Forcing: Decoupling Ego and Object Motion via Sparse Inputs for Structured Video Generation
    Tianshuo Xu, Zhifei Chen, Leyi Wu, Hao Lu, and Yingcong Chen†
    In NeurIPS 2026, 2026
    arXiv HTML PDF
  8. Survey
    In-Context Learning for Robots: Methods and Applications
    Haojian Huang, Zexi Li, Junhao Guo, Yehang Zhang, Wenxuan Peng, Bohan Zhou, Weilin Ruan, Leyi Wu, Chenxu Wang, Jianchong Su, Binghui Xie, Wosong Chen, Yingjie Xu, Tianhao Zhou, Suzeyu Chen, Pukun Zhao, Jiaqi He, Xinyi Li, Runze Li, Peiran Dong, and 19 more authors
    Survey, 2026
    arXiv PDF Code Website
  9. Survey
    A Mechanistic View on Video Generation as World Models: State and Dynamics
    Luozhou Wang*, Zhifei Chen*, Yihua Du, Dongyu Yan, Wenhang Ge, Guibao Shen, Xinli Xu, Leyi Wu, Man Chen, Tianshuo Xu, Peiran Ren, Xin Tao, Pengfei Wan, and Ying-Cong Chen†
    Survey, 2026
    arXiv PDF
  10. Under Review
    flexpainter.png
    FlexPainter: Flexible and Multi-View Consistent Texture Generation
    Dongyu Yan*, Leyi Wu*, Jiantao Lin, Luozhou Wang, Tianshuo Xu, Zhifei Chen, Zhen Yang, Lie Xu, Shunsi Zhang, and Yingcong Chen†
    Under Review, 2025
    arXiv PDF Code Website
  11. CVPR2025
    kiss3d.png
    Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation
    Jiantao Lin*, Xin Yang*, Meixi Chen*, Yingjie Xu, Dongyu Yan, Leyi Wu, Xinli Xu, Lie Xu, Shunsi Zhang, and Ying-Cong Chen†
    In CVPR 2025, 2025
    HTML PDF Code Website
  12. CVPR2025
    uni_renderer.png
    Uni-Renderer: Unifying Rendering and Inverse Rendering Via Dual Stream Diffusion
    Zhifei Chen*, Tianshuo Xu*, Wenhang Ge*, Leyi Wu, Dongyu Yan, Jing He, Luozhou Wang, Lu Zeng, Shunsi Zhang, and Yingcong Chen†
    In CVPR 2025, 2025
    HTML PDF Code
  13. Under Review
    motion_dreamer.png
    Motion Dreamer: Boundary Conditional Motion Reasoning for Physically Coherent Video Generation
    Tianshuo Xu*, Zhifei Chen*, Leyi Wu, Hao Lu, Yuying Chen, Lihui Jiang, Bingbing Liu, and Yingcong Chen†
    Under Review, 2024
    arXiv PDF Code