Xianhui Meng

蒙贤辉

M.S. Candidate

University of Science and Technology of China, Anhui, China

Email: mengxh@mail.ustc.edu.cn
Google Scholar: link

Biography

I am currently a M.S. student in University of Science and Technology of China (USTC) , advised by Prof. Jun Liu.
My research interests focus on computer vision and embodied AI, especially 6D pose estimation and VLA. I am a strong advocate of sharing🌱, collaborating🤝, advancing🚀, and innovating💡. Passionate about bridging fundamental research with real-world impact, I strive to ensure my work contributes to both academic progress and practical value.

If you're interested in collaborating or would like to connect, feel free to reach out via email (邮箱：mengxh@mail.ustc.edu.cn) 😊

News

  • 2026.02: 🎉🎉One paper is accepted by CVPR 2026!
  • 2025.11: 🥳🥳One paper is accepted by AAAI 2026. See you in Singapore!
  • 2025.03: 🎉🎉One paper is accepted by ICME 2025!

Researches

My current research focuses on developing Vision-Language-Action (VLA) models and World Models to empower autonomous driving and embodied agents. By integrating cross-embodiment learning with generative dynamics, I aim to build foundation models that can internalize physical world causalities and execute safe, dexterous actions in unstructured environments.

Selected Publications

Technical Report

  • MiMo-Embodied: X-Embodied Foundation Model Technical Report.

Authors: See Contributions and Acknowledgments section for a full author list.

[Paper] [BibTeX] [Tweet] [Project/Codes]

[TL;DR:] The first cross-embodied foundation model to successfully integrate and achieve SOTA performance in both Autonomous Driving and Embodied AI

CVPR 2026

  • DICArt: Advancing Category-level Articulated Object Pose Estimation in Discrete State-Spaces.

Li Zhang, Mingyu Mei, Ailing Wang, Xianhui Meng, Yan Zhong, Xinyuan Song, Liu Liu, Rujing Wang, Zaixing He, Cewu Lu

[Paper] [BibTeX] [Project/Codes]

[TL;DR:]

AAAI 2026

  • Exploring Category-level Articulated Object Pose Tracking on SE(3) Manifolds.

Xianhui Meng, Yukang Huo, Li Zhang, Liu Liu, Haonan Jiang, Yan Zhong, Pingrui Zhang, Cewu Lu, Jun Liu

[Paper] [BibTeX] [Project/Codes]

[TL;DR:] Pose voting via SE(3)-invarient parameters.

ICME 2025

  • Diff-Art: Category-level Articulation Pose Estimation via Conditional Diffusion.

Yukang Huo, Xianhui Meng, Li Zhang†, Haonan Jiang, Yan Zhong, Mingyuan Yao and Haihua Wang†

[Paper] [BibTeX] [Project/Codes]

[TL;DR:] 6D pose estimation via diffusion model.

TPAMI (under review)

  • Probing Effective and Efficient Category-Level Articulated Object Pose Perception.

Li Zhang, Xianhui Meng, Liu Liu, Haonan Jiang, Jianan Wang, Rujing Wang, Cewu Lu, Jun Liu, Hong Zhang

[Paper] [BibTeX] [Project/Codes]

[TL;DR:] 6D pose tracking by Rotation Decoupled strategy.

Education Experiences

    • 2024.09 - Present: M.S. degree in Information and Communication Engineering, University of Science and Technology of China, Hefei, China
    • 2020.09 - 2024.07: B.S. degree in Automation, Southeast University, Nanjing, China

Services

Conference Service

  • Program Committee Member: ICME25, CVPR26, etc.