Weizhen Wang

Zhou Lab at UCLA, Henry Samueli School of Engineering

/avatar/crop.JPG

I’m a second-year M.S.C.S student at UCLA. Before that, I obtained B.S. in computer science with a minor in mathematics at UCLA, graduating with Cum Laude standing.

I am applying for the Ph.D. program for the Fall 2025 season. My research interests include embodied AI using foundation models and generative modeling. I have experience in end-to-end training of Vision-Language-Models as well as diffusion models, and I have also managed large-scale data. My most proficient programming language is Python, but I have made some frontend projects using JavaScript for research purposes.

For leisure time, I am passionate about skiing, spending almost all my winter breaks in ski resorts for the past four years. Check out my seasonal ski maps (coming) if you are interested. I’m also into LEGO building and Gunpla building.

news

Jun 10, 2025 Another work on hybrid world creation, Dreamland, is now available on arXiv. Many thanks to Sicheng Mo and Ziyang Leng for their dedications.
Jun 10, 2025 Check out our CVPR 2025 workshop on bridging the Sim-to-Real gap, co-hosted by Wayne Wu and Prof. Bolei Zhou, on June 12th.
Jun 01, 2025 One of my latest works, STORK, is now available on arXiv. Special thanks to my collaborator, Zheng Tan, who has such brilliant mathematical intuition.
Feb 17, 2025 My first paper got accepted into CVPR 2025! Special thanks to Zhenghao Peng and Prof. Bolei Zhou for close mentoring.

selected publications

  1. CVPR 2025
    cover_metavqa.gif
    Embodied Scene Understanding for Vision Language Models via MetaVQA
    Weizhen Wang, Chenda Duan, Zhenghao Peng, and 2 more authors
    In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
  2. arXiv Preprint
    stork_teaser.png
    STORK: Improving the Fidelity of Mid-NFE Sampling for Diffusion and Flow Matching Models
    Zheng Tan, Weizhen Wang, Andrea L. Bertozzi, and 1 more author
    2025
  3. arXiv Preprint
    cover_dreamland.gif
    Dreamland: Controllable World Creation with Simulator and Generative Models
    Sicheng Mo, Ziyang Leng, Leon Liu, and 3 more authors
    2025