Fangzhou Mu

fmu at wisc.edu | LinkedIn | Scholar | GitHub | CV

photo.jpg

I research multimodal intelligence and advance Generative AI across data, modeling, and systems optimization.

I am currently an AI Research Scientist at Meta Superintelligence Labs, building world-class video generation and editing models. Previously, I was a Senior Deep Learning Algorithms Engineer at NVIDIA, where I worked on inference optimization of multimodal LLMs.

I graduated with a PhD in Computer Sciences from the University of Wisconsin-Madison, advised by Prof. Yin Li. Before that, I received my Master’s degrees in Computer Sciences and Pharmaceutical Sciences from UW-Madison, and a Bachelor’s degree in Biology from Zhejiang University.

News

Sep 02, 2025 Serving as an Area Chair for CVPR 2026.
Jun 25, 2025 One paper accepted to ICCV 2025.
May 05, 2025 Joining Meta GenAI as an AI Research Scientist!

Selected Publications

  1. mu2024towards.png
    Towards 3D Vision with Low-Cost Single-Photon Cameras
    Fangzhou Mu*Carter Sifferman*Sacha JungermanYiquan Li, Zhiyue Han , Michael GleicherMohit Gupta , and Yin Li
    In Computer Vision and Pattern Recognition (CVPR) , 2024
  2. mu2024snag.png
    SnAG: Scalable and Accurate Video Grounding
    Fangzhou Mu*Sicheng Mo* , and Yin Li
    In Computer Vision and Pattern Recognition (CVPR) , 2024
  3. mo2024freecontrol.png
    FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition
    Sicheng Mo*Fangzhou Mu*Kuan Heng LinYanli Liu, Bochen Guan , Yin Li, and Bolei Zhou
    In Computer Vision and Pattern Recognition (CVPR) , 2024
  4. gutierrez2023learned.png
    Learned Compressive Representations for Single-Photon 3D Imaging
    In International Conference on Computer Vision (ICCV) , 2023
  5. mu2022physics.png
    Physics to the Rescue: Deep Non-Line-of-Sight Reconstruction for High-Speed Imaging
    IEEE Transactions on Pattern Analysis and Machine Intelligence / International Conference on Computational Photography (ICCP), 2022
  6. mu20223d.png
    3D Photo Stylization: Learning to Generate Stylized Novel Views from A Single Image
    Fangzhou MuJian Wang†Yicheng Wu† , and Yin Li†
    In Computer Vision and Pattern Recognition (CVPR) Oral , 2022
  7. xu2022smartadapt.png
    SmartAdapt: Multi-Branch Object Detection Framework for Videos on Mobiles
    In Computer Vision and Pattern Recognition (CVPR) , 2022
  8. mu2020gradients.png
    Gradients as Features for Deep Representation Learning
    Fangzhou MuYingyu Liang , and Yin Li
    In International Conference on Learning Representations (ICLR) , 2020