David Xie

Hello! I’m Qinghongbing Xie, also known as David. Currently pursuing a Master of Engineering in Mechanical Engineering (Intelligent Manufacturing && Robotics) at Tsinghua University, I graduated with a Bachelor of Engineering in Intelligent Manufacturing Engineering && Artificial Intelligence from Beijing Institute of Technology in 2023.

My professional journey features rich internship experiences in leading tech companies. At Pudu Robotics in 2024, I interned in the Pudu X Lab, focusing on the perception of humanoid robots under the guidance of Wu Xiang. Later that year, I joined the Machine Learning RD at DJI, where I worked on the temporal consistency of video semantic segmentation. Currently, I’m interning at Sensetime Technology in SCG, delving into Smart City Spatiotemporal Reasoning LLM.

For more details or to connect, feel free to reach me at binicey@outlook.com or visit my personal website davidxie.online.

Latest Posts

Oct 17, 2025	Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation
Oct 09, 2025	GTR-Bench: Evaluating Geo-Temporal Reasoning in Vision-Language Models
Apr 11, 2025	DSM: Constructing a Diverse Semantic Map for 3D Visual Grounding

Selected Publications

Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation

Xiaoming Zhu, Xu Huang, Qinghongbing Xie, and 8 more authors

ACM Transactions on Graphics, 2025

DOI arXiv Bib PDF Code

@article{zhu2025imaginarium,
  title = {Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation},
  author = {Zhu, Xiaoming and Huang, Xu and Xie, Qinghongbing and Deng, Zhi and Yu, Junsheng and Guan, Yirui and Liu, Zhongyuan and Zhu, Lin and Zhao, Qijun and Liu, Ligang and Zeng, Long},
  journal = {ACM Transactions on Graphics},
  year = {2025},
  eprint = {2510.15564},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  doi = {10.1145/3763353},
  url = {https://arxiv.org/abs/2510.15564},
}

GTR-Bench: Evaluating Geo-Temporal Reasoning in Vision-Language Models

Qinghongbing Xie, Zhaoyuan Xia, Feng Zhu, and 4 more authors

2025

arXiv Bib PDF Code

@misc{xie2025gtrbench,
  title = {GTR-Bench: Evaluating Geo-Temporal Reasoning in Vision-Language Models},
  author = {Xie, Qinghongbing and Xia, Zhaoyuan and Zhu, Feng and Gong, Lijun and Li, Ziyue and Zhao, Rui and Zeng, Long},
  year = {2025},
  eprint = {2510.07791},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  url = {https://arxiv.org/abs/2510.07791},
}

DSM: Constructing a Diverse Semantic Map for 3D Visual Grounding

Qinghongbing Xie, Zijian Liang, Fuhao Li, and 1 more author

2025

arXiv Bib PDF Website

@misc{xie2025dsmbuildingdiversesemantic,
  title = {DSM: Constructing a Diverse Semantic Map for 3D Visual Grounding},
  author = {Xie, Qinghongbing and Liang, Zijian and Li, Fuhao and Zeng, Long},
  year = {2025},
  eprint = {2504.08307},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  url = {https://arxiv.org/abs/2504.08307},
}

Demonstrating DVS: Dynamic Virtual-Real Simulation Platform for Mobile Robotic Tasks

Zijie Zheng, Zeshun Li, Yunpeng Wang, and 2 more authors

2025

arXiv Bib PDF Website

@misc{zheng2025demonstratingdvsdynamicvirtualreal,
  title = {Demonstrating DVS: Dynamic Virtual-Real Simulation Platform for Mobile Robotic Tasks},
  author = {Zheng, Zijie and Li, Zeshun and Wang, Yunpeng and Xie, Qinghongbing and Zeng, Long},
  year = {2025},
  eprint = {2504.18944},
  archiveprefix = {arXiv},
  primaryclass = {cs.RO},
  url = {https://arxiv.org/abs/2504.18944},
}

GRID: Scene-Graph-based Instruction-driven Robotic Task Planning

Zhe Ni, Xiaoxin Deng, Cong Tai, and 5 more authors

In 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024

DOI arXiv Bib PDF Website

@inproceedings{10801291,
  author = {Ni, Zhe and Deng, Xiaoxin and Tai, Cong and Zhu, Xinyue and Xie, Qinghongbing and Huang, Weihang and Wu, Xiang and Zeng, Long},
  booktitle = {2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  title = {GRID: Scene-Graph-based Instruction-driven Robotic Task Planning},
  year = {2024},
  volume = {},
  number = {},
  pages = {13765-13772},
  keywords = {Accuracy;Grounding;Large language models;Semantics;Pipelines;Real-time systems;Planning;Robots;Intelligent robots;Synthetic data},
  doi = {10.1109/IROS58592.2024.10801291},
}