Juyi Lin

profile.png

I am a second-year PhD student at Northeastern University advised by Prof. Yanzhi Wang. I earned my bachelor’s degree from Zhejiang University in 2022 and MSCS degree from KAUST in 2023, where I was advised by Prof. Marco Canini.

My research interests lie on Generative Model for physics world. I am currently exploring opportunities for internships.

I’m always happy to collaborate with graduate/undergraduate students. Please drop me an email if you want to work with me. Feel free to reach out if you’re interested in my research.

news

May 18, 2026 Joined Futurewei Technologies, Inc. as a Research Intern, Generative AI & World Modeling (Full-time).
May 13, 2026 🎉 Releasing PhyGround (first author) — a benchmark for the physical plausibility of image-to-video generation: 250 physics-aware prompts, 8 ti2v models scored on 3 general + 13 physical-law rubrics, plus a human-aligned judge model. Paper: arXiv Dataset: HuggingFace Code: GitHub.
May 13, 2026 A Very Big Video Reasoning Suite is accepted by ICML 2026! Paper:A Very Big Video Reasoning Suite (co-first author) Dataset: HuggingFace Code: GitHub.

selected publications

  1. ICML
    VBVR_Teaser.png
    A Very Big Video Reasoning Suite
    Maijunxian Wang*, Ruisi Wang*, Juyi Lin*, Ran Ji*, Thaddäus Wiedemer, Qingying Gao, Dezhi Luo, and others
    In International Conference on Machine Learning (ICML), 2026
    Paper Video Code Website
  2. arXiv
    phyground_teaser.png
    PhyGround: Benchmarking Physical Reasoning in Generative World Models
    Juyi Lin, Arash Akbari, Yumei He, Lin Zhao, Haichao Zhang, Arman Akbari, Xingchen Xu, Zoe Y. Lu, Enfu Nan, Hokin Deng, Edmund Yeh, Sarah Ostadabbas, Yun Fu, Jennifer Dy, Pu Zhao, and Yanzhi Wang
    2026
    Paper Code Poster Slides Website
  3. ICANN 2026
    VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting
    Juyi Lin, Amir Taherin, Arash Akbari, Arman Akbari, Lei Lu, Guangyu Chen, Taskin Padir, Xiaomeng Yang, Weiwei Chen, Yiqian Li, Xue Lin, David Kaeli, Pu Zhao, and Yanzhi Wang
    2025
    Paper Code Slides
  4. NeurIPS
    ALTER: All-in-One Layer Pruning and Temporal Expert Routing for Efficient Diffusion Generation
    Xiaomeng Yang*, Lei Lu*, Qihui Fan, Changdi Yang, Juyi Lin, Yanzhi Wang, Xuan Zhang, and Shangqian Gao
    2025
    Paper Code