Sihang LI

back.jpeg
Salt lake, China, 2019

I am a second-year PhD student at NYU AI4CE Lab led by Chen Feng. Before my Ph.D journey, I worked as a research assistant at Hong Kong University of Science and Technology (HKUST) in 2023 and I received B.E. degree at Tongji Univerisity (TJU) advised by Changhong Fu in Jul. 2022.

My research lies in the intersection of robotics and spatial intelligence, whose goal is to drastically improve robotic reliability, intelligence and security in complex scenarios. These works are motivated by the urgent need of 3D representation learning for robotics with minimal supervision and spatial reasoning with multiple sensors, such as inferring a complete model of a scene with image/language/point cloud information. More specifically, my research interests include: (1) computer vision and robotics: collaborative perception, 3D scene understanding, video understanding; (2) machine learning: adversarial learning, representation Learning, and multimodal learning; (3) applications: self-driving, robotics, construction automation, and human-robot interaction.

:speaker: I am looking for UG/MS students to work on cutting-edge research projects with me and my collaborators at NYU/NVIDIA/USC/Tsinghua. Please send me an email if you are interested!

  • Efficient Visual Localization for Spatial Robotics
  • Neural Representations for Large-scale Scenes
  • Imitation Learning for Robot Manipulation
  • Foundation Models for Robotic Perception and Planning

news

Sep 25, 2024 :tada: MSG are accepted by NeurIPS 2024. See you in Vancouver!
Sep 1, 2024 :tada: I successfully became a Ph.D candidate, by passing my Ph.D qualifying exam on the topic of Robust Visual Localization for Robotics.
Jun 30, 2024 :tada: SSCBench and DSRNSS are accepted by IROS 2024. Both works try to solve the challenges in perception for autonomous driving! See you in Abu Dhabi!
Sep 1, 2023 My Ph.D journey in NYU begins! I am supervised by Prof. Chen Feng.
Jan 1, 2023 :tada: SGDViT and ClimRT are accepted by ICRA 2023. See you in London!
Dec 1, 2022 :tada: TRTrack and ABDNet are accepted by RA-L 2022.
Sep 1, 2022 :books: My life in HKUST as a research assistant begins!
Jul 23, 2022 :tada: LPAT, FDNT and HighlightNet are accepted at IROS 2022. See you in Kyoto!
Jun 25, 2022 :books: I finish my bachelor degree with excellent graduation thesis at Tongji university!
Feb 1, 2022 :tada: Ad^2 Attack is accepted by ICRA 2022.

selected publications

2024

  1. NeurIPS
    msg.png
    Multiview Scene Graph
    Juexiao Zhang, Gao Zhu, Sihang Li, and 4 more authors
    In Advances in Neural Information Processing Systems, 2024
  2. IROS
    sscbench.gif
    SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving
    Yiming Li, Sihang LiXinhao Liu, and 8 more authors
    In IEEE/RSJ International Conference on Intelligent Robots and Systems, 2024

2023

  1. IROS
    DSRNSS.png
    Towards Dynamic and Small Objects Refinement for Unsupervised Domain Adaptative Nighttime Semantic Segmentation
    Jingyi Pan, Sihang Li, Yucheng Chen, and 2 more authors
    In IEEE/RSJ International Conference on Intelligent Robots and Systems, 2023
  2. RA-L
    trtrack.png
    Boosting UAV Tracking with Voxel-based Trajectory-Aware Pre-Training
    Sihang LiChanghong FuKunhan Lu, and 3 more authors
    IEEE Robotics and Automation Letters, 2023
  3. RA-L
    abdnet.png
    Adversarial Blur-Deblur Network for Robust UAV Tracking
    Haobo ZuoChanghong FuSihang Li, and 3 more authors
    IEEE Robotics and Automation Letters, 2023
  4. ICRA
    climrt.png
    Continuity-aware latent interframe information mining for reliable UAV tracking
    Changhong Fu, Mutian Cai, Sihang Li, and 3 more authors
    In IEEE International Conference on Robotics and Automation, 2023
  5. ICRA
    sgdvit.png
    SGDViT: saliency-guided dynamic vision transformer for UAV tracking
    Liangliang Yao, Changhong FuSihang Li, and 2 more authors
    In IEEE International Conference on Robotics and Automation, 2023

2022

  1. IROS
    fdnt.png
    End-to-end feature decontaminated network for UAV tracking
    Haobo ZuoChanghong FuSihang Li, and 2 more authors
    In IEEE/RSJ International Conference on Intelligent Robots and Systems, 2022
  2. IROS
    lpat.png
    Local perception-aware transformer for aerial tracking
    Changhong Fu, Weiyu Peng, Sihang Li, and 2 more authors
    In IEEE/RSJ International Conference on Intelligent Robots and Systems, 2022
  3. IROS
    highlightnet.png
    HighlightNet: highlighting low-light potential features for real-time UAV tracking
    Changhong Fu, Haolin Dong, Junjie Ye, and 3 more authors
    In IEEE/RSJ International Conference on Intelligent Robots and Systems, 2022
  4. ICRA
    ad2attack.png
    Ad 2 attack: Adaptive adversarial attack on real-time uav tracking
    Changhong FuSihang Li, Xinnan Yuan, and 3 more authors
    In International Conference on Robotics and Automation, 2022