Sirui Xu  
(徐 思睿)

Ph.D. @ UIUC

prof_pic.jpg

I am a second-year CS Ph.D. student at the University of Illinois Urbana-Champaign, advised by Prof. Yuxiong Wang and Prof. Liangyan Gui. Before that, I obtained my M.S. degree from University of Illinois Urbana-Champaign and B.S. degree from Peking University.

My main research areas are computer vision, computer graphics and machine learning, revolving around the fundamental challenge of enabling machines to interpret and model humans and their behaviors, as well as their interactions with surrounding virtual or physical world, with applications in simulation and robotics.

I am always opened for discussion and collaboration, drop me an email if you are interested.

news

Sep 26, 2024 Our paper, InterDreamer, has been accepted by NeurIPS 2024.
Mar 29, 2024 Passed my qualifying exam. I am a whole PhD candidate now!
Mar 28, 2024 Our paper “InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction” is posted on arXiv. Check our project page.
Jan 10, 2024 I will be joining the NVIDIA Seattle Robotics Lab as a PhD research intern in Summer 2024.
Sep 30, 2023 I will be attending ICCV 2023 in person to present our work “InterDiff”. Feel free to come by our poster session at Room “Foyer Sud” 089 on Thursday afternoon.
Jul 13, 2023 Our work “InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion” is accepted at ICCV 2023.
May 24, 2023 I presented a talk at Electronic Arts on the topic of diverse sampling in human motion prediction.
Apr 15, 2023 I will be starting my Ph.D. at UIUC (after finishing my MS here).
Jan 20, 2023 Our paper “Stochastic Multi-Person 3D Motion Forecasting” got accepted as a notable-top-25%(spotlight) paper at ICLR 2023.
Jul 8, 2022 Our paper “Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors” was accepted to ECCV 2022 for an oral presentation. Check our project page for code and documentation.
Mar 15, 2021 I will become a M.S. student at UIUC this fall.

selected publications

  1. InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction
    Sirui XuZiyin Wang, Yu-Xiong Wang, and 1 more author
    In NeurIPS 2024
  2. InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion
    Sirui XuZhengyuan Li, Yu-Xiong Wang, and 1 more author
    In ICCV 2023
  3. Spotlight
    Stochastic Multi-Person 3D Motion Forecasting
    Sirui Xu, Yu-Xiong Wang, and Liang-Yan Gui
    In ICLR 2023
  4. Oral
    Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors
    Sirui Xu, Yu-Xiong Wang, and Liang-Yan Gui
    In ECCV 2022