Sicheng Mo

sicheng/photo_01.jpg

I am a fourth-year PhD student in Computer Science at UCLA, where I am being advised by Prof. Bolei Zhou. I earned my Bachelor’s degree in Computer Science and Applied Mathematics from the University of Wisconsin-Madison, during which I conducted research under the guidance of Prof. Yin Li and Prof. Fred Sala.

My research lies in Computer Vision and Multi-modal Learning. I am particularly interested in large multi-modal generative models, with a focus on controllable generation of images, videos, and interactive worlds. I also worked on scalable language-driven video understanding and 3D reconstruction before.

I am actively looking for a full-time research internship for Summer 2027. Please feel free to reach out if you believe my background would be a good fit for your team.

News

Jul 24, 2026 Check out our recent work WorldWeaver and UniTemp.
Feb 21, 2026 Two papers accepted to CVPR 2026! Checkout our GroupDiff and Relational Visual Similarity.
Jun 25, 2025 X-Fusion has been accepted to ICCV 2025 and received the Best Paper Award at the CVPR 2025 T4V Workshop.

Selected publications

* indicates equal contribution

  1. arXiv
    Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers
    Sicheng Mo*, Yuheng Li*, Ziyang Leng, Krishna Kumar Singh, and Bolei Zhou
    In arXiv, 2026
    Website PDF Code
  2. CoRL
    DreamStream: Towards Policy-Oriented Generative Simulation for End-to-End Driving
    Ziyang Leng*, Sicheng Mo*, Seth Z. Zhao, Haoyuan Cai, Yu Zeng, Rowan McAllister, and Bolei Zhou
    In Conference on Robot Learning (CoRL), 2026
    Website PDF Code
  3. groupdiff_thumbnail.jpg
    CVPR
    Group Diffusion: Enhancing Image Generation by Unlocking Cross-Sample Collaboration
    Sicheng Mo, Thao Nguyen, Richard Zhang, Nicholas Kolkin, Siddharth Srinivasan Iyer, Eli Shechtman, Krishna Kumar Singh, Yong Jae Lee, Bolei Zhou, and Yuheng Li
    In Computer Vision and Pattern Recognition (CVPR), 2026
    Website PDF Code
  4. dreamland_thumbnail.png
    Arxiv
    Dreamland: Controllable World Creation with Simulator and Generative Models
    Sicheng Mo*, Ziyang Leng*, Leon Liu, Weizhen Wang, Honglin He, Zhang Huizhi, and Bolei Zhou
    In ArXiv, 2025
    Website PDF
  5. xfusion_thumbnail.png
    Arxiv
    X-Fusion: Introducing New Modality to Frozen Large Language Models
    Sicheng Mo, Thao Nguyen, Xun Huang, Siddharth Srinivasan Iyer, Yijun Li, Yuchen Liu, Abhishek Tandon, Eli Shechtman, Krishna Kumar Singh, Yong Jae Lee, Bolei Zhou, and Yuheng Li
    In International Conference on Computer Vision (ICCV) , 2025
    Best Paper at CVPR 2025 T4V Workshop
    Website PDF
  6. ctrl-x.jpg
    NeurIPS
    Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance
    Kuan Heng Lin*, Sicheng Mo*, Ben Klingher, Fangzhou Mu, and Bolei Zhou
    In Advances in Neural Information Processing Systems (NeurIPS), 2024
    Website PDF
  7. freecontrol1.jpg
    CVPR
    FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition
    Sicheng Mo*, Fangzhou Mu*, Kuan Heng Lin, Yanli Liu, Bochen Guan, Yin Li, and Bolei Zhou
    In Computer Vision and Pattern Recognition (CVPR), 2024
    Website PDF Code
  8. snag.png
    CVPR
    SnAG: Scalable and Accurate Video Grounding
    Fangzhou Mu*, Sicheng Mo*, and Yin Li
    In Computer Vision and Pattern Recognition (CVPR), 2024
    Website PDF