Jiangyong Huang

PKU & BIGAI, Beijing, China

prof_pic.jpg

  • I am currently a Ph.D. student at Peking University (PKU), advised by Prof. Song-Chun Zhu. I major in artificial intelligence (AI) with a primary focus on computer vision (CV). Before Ph.D., I graduated from PKU and obtained my Bachelor’s degree in 2022.

  • My research interests include multi-modal model, 3D scene understanding, and embodied AI. My research goal is to develop embodied generalist agents capable of (1) understanding the 3D world, and (2) following human instructions to interact with the 3D world.

News

Jan, 2026 SceneCOT is accepted by ICLR 2026
Apr, 2025 Check out CVPR 2025 Challenge: ARNOLD (Embodied AI) and MSQA (3D Scene Understanding)
Feb, 2025 Beacon3D is accepted by CVPR 2025
Sep, 2024 MSR3D is accepted by NeurIPS 2024
May, 2024 LEO is accepted by ICML 2024
Mar, 2024 Check out CVPR 2024 Challenge: ARNOLD (Embodied AI)
Jul, 2023 ARNOLD is accepted by ICCV 2023
Sep, 2022 Start my Ph.D. at PKU
Jun, 2022 Graduate and obtain Bachelor’s degree from PKU

Publications

  1. SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenes
    Xiongkun Linghu, Jiangyong Huang, Ziyu Zhu, Baoxiong Jia, and Siyuan Huang
    ICLR 2026
    arXiv Website Code
  2. LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning
    Jiangyong Huang, Xiaojian Ma, Xiongkun Linghu, Yue Fan, Junchao He, Wenxin Tan, Qing Li, Song-Chun Zhu, Yixin Chen, Baoxiong Jia, and Siyuan Huang
    Preprint
    arXiv Website Code
  3. 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, Song-Chun Zhu, and Siyuan Huang
    CVPR 2025
    arXiv Website Code
  4. Multi-modal Situated Reasoning in 3D Scenes
    Xiongkun Linghu*, Jiangyong Huang*, Xuesong Niu*, Xiaojian Ma, Baoxiong Jia, and Siyuan Huang
    NeurIPS 2024
    arXiv Website Code
  5. An Embodied Generalist Agent in 3D World
    Jiangyong Huang*, Silong Yong*, Xiaojian Ma*, Xiongkun Linghu*, Puhao Li, Yan Wang, Qing Li, Song-Chun Zhu, Baoxiong Jia, and Siyuan Huang
    ICML 2024
    arXiv Website Code
  6. ARNOLD: A Benchmark for Language-Grounded Task Learning With Continuous States in Realistic 3D Scenes
    Ran Gong*, Jiangyong Huang*, Yizhou Zhao, Haoran Geng, Xiaofeng Gao, Qingyang Wu, Wensi Ai, Ziheng Zhou, Demetri Terzopoulos, Song-Chun Zhu, Baoxiong Jia, and Siyuan Huang
    ICCV 2023
    arXiv Website Code
  7. Perceive, Ground, Reason, and Act: A Benchmark for General-purpose Visual Representation
    Jiangyong Huang*, William Yicheng Zhu*, Baoxiong Jia, Zan Wang, Xiaojian Ma, Qing Li, and Siyuan Huang
    Preprint
    arXiv Website Code

Experiences

2022 - Now Reviewer for NeurIPS, CVPR, ICLR, ECCV, ICML, AAAI, RA-L
2021 - Now Research intern at BIGAI
Fall, 2022 & 2023 TA for Statistical Vision at PKU
Summer, 2022 TA for Directed Research in AI System at PKU
Spring, 2021 Intern at AI Innovation Center, PKU
2019 - 2020 PKU annual scholarship and award
2018 - 2019 PKU annual scholarship and award