YIMING LI

Dean's PhD Fellow @ NYU | NVIDIA Fellow (2024-2025)

headshot.jpeg

I am a Dean’s PhD Fellow at NYU, advised by Institute Associate Professor Chen Feng and collaborating with Prof. Saining Xie. I am also a Graduate Fellow at NVIDIA Research, working on world simulators and foundation models with Prof. Marco Pavone at Stanford University. I am fortunate to collaborate with Dr. Zhiding Yu at Learning and Perception Research, as well as Dr. Zan Gojcjc and Prof. Sanja Fidler at Toronto AI Lab.

Previously, I spent some time at NVIDIA Applied AV Research with Dr. Jose M. Alvarez, NVIDIA AI Research with Prof. Anima Anandkumar, Tsinghua MARS Lab with Prof. Hang Zhao, and SJTU with Prof. Siheng Chen.

My research aims to replicate human-like spatial intelligence with minimal human supervision, paving the way for trustworthy and accessible autonomous robots and embodied agents working for and around humans. My current efforts are in three dimensions: (1) agent: building a generalist embodied visual agent powered by foundation models to perceive and act in 3D; (2) world: building a photorealistic world simulator to train and evaluate the foundation agents; (3) data: visual-spatial and multimodal dataset curation.

news

Oct 31, 2024 I successfully passed my PhD defense [video]. Many thanks to my committee and collaborators!
Jul 23, 2024 MARS is covered by TechXplore: New dataset kicks autonomous vehicle research into high gear.
Jun 01, 2024 We are organizing the 2nd Vision-Centric Autonomous Driving (VCAD) Workshop at ECCV 2024.
May 20, 2024 I serve as an Associate Editor for IROS 2024.
Dec 10, 2023 I am honored to receive the NVIDIA Graduate Fellowship (2024-2025) (10 awardees worldwide).

selected publications

2024

  1. NeurIPS Spotlight
    3dgm.png
    Memorize What Matters: Emergent Scene Decomposition from Multitraverse
    Yiming Li, Zehong Wang, Yue Wang, and 5 more authors
    In Advances in Neural Information Processing Systems, 2024
  2. CVPR
    mars.png
    Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset
    Yiming Li, Zhiheng Li, Nuo Chen, and 5 more authors
    In IEEE Conference on Computer Vision and Pattern Recognition, 2024

2023

  1. RSS
    deepexplorer.png
    Metric-Free Exploration for Topological Mapping by Task and Motion Imitation in Feature Space
    Yuhang He, Irving Fang, Yiming Li, and 2 more authors
    In Proceedings of Robotics: Science and Systems, 2023
  2. CVPR Highlight
    voxformer.png
    VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion
    Yiming Li, Zhiding Yu, Christopher Choy, and 5 more authors
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

  1. CVPR
    egopat3d.png
    Egocentric Prediction of Action Target in 3D
    Yiming Li, Ziang Cao, Andrew Liang, and 4 more authors
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2022

2021

  1. NeurIPS
    disconet.png
    Learning Distilled Collaboration Graph for Multi-Agent Perception
    Yiming Li, Shunli Ren, Pengxiang Wu, and 3 more authors
    In Advances in Neural Information Processing Systems, Jun 2021
  2. ICCV Oral
    flat.gif
    Fooling LiDAR Perception via Adversarial Trajectory Perturbation
    Yiming Li, Congcong Wen, Felix Juefei-Xu, and 1 more author
    In IEEE International Conference on Computer Vision, Jun 2021