Hongyu Li (李鸿宇)

headshot.jpg

Credit: Tianyu Zhang
Email | Google Scholar
CV | X | LinkedIn

Welcome! I am a third-year Ph.D. candidate in Computer Science at Brown University, advised by Prof. George Konidaris. I’m currently visiting Prof. Yunzhu Li’s lab at Columbia University, supported by a generous research fellowship from Brown University. My research interests revolve around the convergence of robotics, machine learning, and computer vision, particularly in the co-design of multi-modal perception and planning. My current focus is on developing deep learning models for environmental and object interaction, specifically leveraging tactile sensing and world models (video and particle-based).

I interned at Robotics and AI Institute (formerly Boston Dynamics AI Institute), Amazon Robotics (Innovation Lab), and Honda Research Institute. Before joining Brown University, I worked with Prof. Huaizu Jiang and Prof. Taskin Padir at Northeastern University.

I serve as a reviewer for conferences such as ICRA, IROS, RSS, CVPR, ECCV, ICCV, WACV, Humanoids, AAAI, HRI, and CHI, as well as journals including T-RO, RA-L.

I’m happy to chat about research or life — just send me an email.

News

Jan 31, 2026 My work during RAI internship, NovaFlow, is accepted by ICRA 2026. See you in Vienna :austria:!
Jan 8, 2026 I will join NVIDIA as a research intern.
Jun 6, 2025 I delivered an oral presentation at the New England Manipulation Symposium (NEMS).
Apr 11, 2025 V-HOP is accepted by RSS 2025. See you in Los Angeles :us:!
Apr 1, 2025 I will join Robotics and AI Institute as a research intern.

Experience

  1. Experience

    NVIDIA
    Incoming
    Research Intern
    Hosts: Bowen Wen, Xinghao Zhu, and Yan Chang

  2. Experience

    Robotics and AI Institute (formerly Boston Dynamics AI Institute)
    06/2025 - 01/2026
    Research Intern
    Hosts: Jiahui Fu and Lingfeng Sun

  3. Experience

    Amazon Robotics (Innovation Lab)
    05/2024 - 09/2024
    Applied Scientist II Intern
    Hosts: Taskin Padir and Tye Brady

  4. Experience

    Honda Research Institute USA
    09/2022 - 12/2022, 05/2023 - 08/2023
    Research Intern
    Hosts: Nawid Jamali and Soshi Iba

Publications

By default, only selected papers are shown. Symbol * or † represents equal contribution or advising.

2026

  1. ICRA
    novaflow.gif
    NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos
    Hongyu Li*, Lingfeng Sun*, Yafei Hu, Duy Ta, Jennifer Barry, George Konidaris, and Jiahui Fu
    In IEEE International Conference on Robotics and Automation (ICRA), 2026
    arXiv HTML PDF

2025

  1. arXiv
    unitac.gif
    UniTac: Whole-Robot Touch Sensing Without Tactile Sensors
    Wanjia Fu*, Hongyu Li*, Ivy X. He, Stefanie Tellex, and Srinath Sridhar
    Preprint
    Presented at RSS 2025 HRCM workshop.
    arXiv HTML
  2. RSS
    v-hop.gif
    V-HOP: Visuo-Haptic 6D Object Pose Tracking
    Hongyu Li, Mingxi Jia, Tuluhan Akbulut, Yu Xiang, George Konidaris, and Srinath Sridhar
    In Robotics: Science and Systems (RSS), 2025
    Oral presentation at New England Manipulation Symposium (NEMS).
    Presented at ICRA 2025 ViTac workshop.
    arXiv HTML Code
  3. ICRA
    vita-zero.gif
    ViTa-Zero: Zero-shot Visuotactile Object 6D Pose Estimation
    Hongyu Li, James Akl, Srinath Sridhar, Tye Brady, and Taskin Padir
    In IEEE International Conference on Robotics and Automation (ICRA), 2025
    Unfortunately, we are unable to publish the code and the dataset per the company policy.
    arXiv HTML PDF

2024

  1. IROS
    odtformer.gif
    ODTFormer: Efficient Obstacle Detection and Tracking with Stereo Cameras Based on Transformer
    Tianye Ding*, Hongyu Li*, and Huaizu Jiang
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024
    arXiv HTML PDF Code
  2. IROS
    hypertaxel.gif
    HyperTaxel: Hyper-Resolution for Taxel-Based Tactile Signal Through Contrastive Learning
    Hongyu Li, Snehal Dikhale, Jinda Cui, Soshi Iba, and Nawid Jamali
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024
    Unfortunately, we are unable to publish the code and the dataset per the company policy.
    arXiv PDF
  3. IROS
    snn.gif
    StereoNavNet: Learning to Navigate using Stereo Cameras with Auxiliary Occupancy Voxels
    Hongyu Li, Taskin Padir, and Huaizu Jiang
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024
    arXiv PDF
  4. RA-L
    e2-preview.png
    E(2)-Equivariant Graph Planning for Navigation
    Linfeng Zhao*, Hongyu Li*, Taskin Padir, Huaizu Jiang†, and Lawson L.S Wong†
    IEEE Robotics and Automation Letters, 2024
    Presented at IROS 2024 (Oral) in Abu Dhabi, UAE :camel:.
    arXiv HTML PDF Code

2023

  1. thesis-animation.gif
    Toward Efficient Stereo-based Obstacle Detection Using Deep Neural Network
    Hongyu Li
    Northeastern University, 2023
  2. RA-L
    vihope-animation.gif
    ViHOPE: Visuotactile In-Hand Object 6D Pose Estimation with Shape Completion
    Hongyu Li, Snehal Dikhale, Soshi Iba, and Nawid Jamali
    IEEE Robotics and Automation Letters, 2023
    Unfortunately, we are unable to publish the code and the dataset per the company policy.
    Presented at ICRA 2024 in Yokohama, Japan :jp:.
    Presented at NeurIPS 2023 Workshop on Touch Processing in New Orleans, LA :us:.
    arXiv PDF
  3. ICRA
    hie.gif
    StereoVoxelNet: Real-Time Obstacle Detection Based on Occupancy Voxels from a Stereo Camera Using Deep Neural Networks
    Hongyu Li, Zhengang Li*, Neset Unver Akmandor*, Huaizu Jiang, Yanzhi Wang, and Taskin Padir
    In IEEE International Conference on Robotics and Automation (ICRA), 2023
    Presented at IROS 2022 Agile Robotics Workshop in Kyoto, Japan :jp:.
    arXiv HTML PDF Supp Code

2022

  1. IROS
    tentabot.gif
    Deep Reinforcement Learning based Robot Navigation in Dynamic Environments using Occupancy Values of Motion Primitives
    Neset Unver Akmandor, Hongyu Li, Gary Lvov, Eric Dusel, and Taskin Padir
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022
    arXiv PDF Code