Xiongkun Linghu

personal_img.jpg

I am currenctly a Phd student at Peking University, supervised by Prof. Yiwu Zhong. I was a researcher at Beijing Academy of Artificial Intelligence (BAAI) from March 2026 to August 2026. Before that, I was a senior research engineer at Beijing Institute for General Artificial Intelligence (BIGAI) from July 2023 to March 2026. In BIGAI, I was advised by Dr. Siyuan Huang and Dr. Baoxiong Jia. I obtained my M.Eng. from Tsinghua University in July 2023. Previously, I received my B.S. from Beijing Institute of Technology in July 2020.

I am generally interested in multimodal foundation models and embodied AI. My long-term goal is building powerful, reliable and safe embodied agents in the digital and physical world. Please feel free to contact me if you are interested in collaborating!

News

  • May 2026: I am recognized as the Gold Reviewer of ICML 2026.
  • May 2026: 3D-RFT is accepted by ICML 2026.
  • January 2026: SceneCOT is accepted by ICLR 2026.

Selected Publications

  1. 3D-RFT.png
    3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understanding
    Xiongkun Linghu*, Jiangyong Huang*, Baoxiong Jia, and Siyuan Huang
    ICML 2026
    arXiv HTML Code
  2. scenecot.png
    SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenes
    Xiongkun Linghu, Jiangyong Huang, Ziyu Zhu, Baoxiong Jia, and Siyuan Huang
    ICLR 2026
    arXiv HTML Code
  3. beacon3d.png
    Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis
    Jiangyong Huang* ,Baoxiong Jia*, Yan Wang, Ziyu Zhu, Xiongkun Linghu, Qing Li, Songchun Zhu, and Siyuan Huang
    CVPR 2025
    arXiv HTML Code
  4. msr3d.png
    Multi-modal Situated Reasoning in 3D Scenes
    Xiongkun Linghu*, Jiangyong Huang* , Xuesong Niu*, Xiaojian Ma, Baoxiong Jia, and Siyuan Huang
    NeurIPS, Datasets and Benchmarks Track, 2024
    arXiv HTML Code
  5. LEO.png
    An Embodied Generalist Agent in 3D World
    Jiangyong Huang*, Silong Yong*, Xiaojian Ma*, Xiongkun Linghu*, Puhao Li, Yan Wang, Qing Li, Songchun Zhu, Baoxiong Jia, and Siyuan Huang
    ICML, 2024
    arXiv HTML Code Demo

Preprint

  1. bel.jpg
    Bayesian Evidential Learning for Few-Shot Classification
    Xiongkun Linghu, Yan Bai, Yihang Lou, Shengsen Wu,Jinze Li, Jianzhong He, and Tao Bai
    arxiv, 2022
    arXiv

Service

    • Reviewers: I serve as the reviewer for NeurIPS, ICML, ICLR, CVPR, and ECCV

Honors and Awards

    • ICML 2026 Gold Reviewer
    • The excellent student in Beijing Institute of Technology

Experience

    • 2026.8 - now, Phd Student, School of Intelligence Science and Technology, Peking University
    • 2026.3 - 2026.8, Researcher, Embodied Model Research Group, BAAI
    • 2023.7 - 2026.3, Senior Research Engineer, Embodied Robtics Center, BIGAI
    • 2021.12 - 2022.7, Intern, Machine Vision, Huawei
    • 2021.5 - 2021.11, Intern, Video Group, Megvii

Education

    • 2020.8 - 2023.6, M.Eng. in Electronic Information, Tsinghua University
    • 2016.8 - 2020.6, B.S. in Electronic Information Engineering, Beijing Institute of Technology