Sicheng Mo

my_photo/sm2.jpg

I am currently a second-year Master of Science 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. I am particularly interested in large generative models for visual content generation and understanding. I also worked on scalable language-driven video understanding and 3D reconstruction before.

In the past, my work extended to the field of machine learning, specifically on causal inference for Out-of-distribution generalization.

news

Feb 26, 2024 Two papers accepted to CVPR 2024! Thanks to my collaborators and advisors!
Sep 20, 2022 Our team wins the second prize for ECCV 2022 Ego4D NLQ and MQ challenges. See our technical report here.
Jun 14, 2022 Our paper Causal Omnivore: Fusing Noisy Estimates of Spurious Correlations is accepted to Workshop on Spurious Correlations, Invariance, and Stability at ICML’22 Workshop!

selected publications

  1. freecontrol1.jpg
    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
    HTML PDF
  2. snag.png
    SnAG: Scalable and Accurate Video Grounding
    Fangzhou Mu* , Sicheng Mo*, and Yin Li
    In Computer Vision and Pattern Recognition (CVPR) , 2024
  3. vigformer.png
    A Simple Transformer-Based Model for Ego4D Natural Language Queries Challenge
    Sicheng Mo, Fangzhou Mu , and Yin Li
    In arXiv , Oct 2022
    HTML PDF
  4. actionformer.png
    Where a Strong Backbone Meets Strong Features–ActionFormer for Ego4D Moment Queries Challenge
    Fangzhou Mu , Sicheng Mo, Gillian Wang , and Yin Li
    In arXiv , Oct 2022
    HTML PDF
  5. cas.png
    Causal Omnivore: Fusing Noisy Estimates of Spurious Correlations
    Dyah Adila , Sonia Cromp , Sicheng Mo, and Frederic Sala
    In ICML’22 Workshop on Spurious Correlations, Invariance, and Stability , Jun 2022
    PDF
  6. iccp.jpg
    Physics to the Rescue: Deep Non-line-of-sight Reconstruction for High-speed Imaging
    Fangzhou Mu , Sicheng Mo, Jiayong Peng , Xiaochun Liu , Ji Hyun Nam , Siddeshwar Raghavan , Andreas Velten , and Yin Li
    In ICCP/TPAMI , Jun 2022
    HTML PDF