@misc{lu2026physislang,
  title = {Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model},
  author = {Lu, Liming and Ma, Xianzheng and He, Wenkun and Zhan, Guanqi and Zhao, Yilin and Chen, Junyu and Xu, Mengyao and Fan, Jiaojiao and Ge, Wenhang and Gu, Yuchao and Liu, Yunze and Li, Boyi and Dong, Zhen and Prisacariu, Victor and Liu, Ming-Yu and Han, Song and Cai, Han},
  year = {2026},
  eprint = {2609.40358},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2609.40358}
}

@inproceedings{egm2026,
  title = {EGM: Efficient Visual Grounding Language Models},
  author = {Zhan, Guanqi and Li, Changye and Liu, Zhijian and Lu, Yao and Wu, Yi and Han, Song and Zhu, Ligeng},
  booktitle = {ECCV},
  year = {2026},
  url = {https://arxiv.org/abs/2601.13633}
}

@inproceedings{idpp2026,
  title = {Inferring Dynamic Physical Properties from Video Foundation Models},
  author = {Zhan, Guanqi and Ma, Xianzheng and Xie, Weidi and Zisserman, Andrew},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (VGBE)},
  year = {2026},
  url = {https://arxiv.org/abs/2510.02311}
}

@inproceedings{gr3d2026,
  title = {Grounded 3D-Aware Spatial Vision-Language Modeling},
  author = {Cheng, An-Chieh and Fu, Yang and Ji, Yatai and Zhu, Ligeng and Zhan, Guanqi and Zhang, Zhuoyang and Yang, Zhaojing and Han, Song and Lu, Yao and Molchanov, Pavlo and Murali, Vidya Nariyambut and Kautz, Jan and Wang, Xiaolong and Yin, Hongxu and Liu, Sifei},
  booktitle = {CVPR},
  year = {2026},
  url = {https://arxiv.org/abs/2605.30307}
}

@article{targo2026,
  title = {TARGO and TARGO-Net: Benchmarking Target-driven Object Grasping under Occlusions},
  author = {Xia, Yan and Ding, Ran and Qin, Ziyuan and Zhan, Guanqi and Zhou, Kaichen and Yang, Long and Dong, Hao and Cremers, Daniel},
  journal = {International Journal of Computer Vision},
  year = {2026},
  url = {https://arxiv.org/abs/2407.06168}
}

@inproceedings{elip2025,
  title = {ELIP: Enhanced Visual-Language Foundation Models for Image Retrieval},
  author = {Zhan, Guanqi and Liu, Yuanpei and Han, Kai and Xie, Weidi and Zisserman, Andrew},
  booktitle = {International Conference on Content-Based Multimedia Indexing},
  year = {2025},
  url = {https://arxiv.org/abs/2502.15682}
}

@inproceedings{physical2024,
  title = {A General Protocol to Probe Large Vision Models for 3D Physical Understanding},
  author = {Zhan, Guanqi and Zheng, Chuanxia and Xie, Weidi and Zisserman, Andrew},
  booktitle = {NeurIPS},
  year = {2024},
  url = {https://arxiv.org/abs/2310.06836}
}

@inproceedings{amodal2024,
  title = {Amodal Ground Truth and Completion in the Wild},
  author = {Zhan, Guanqi and Zheng, Chuanxia and Xie, Weidi and Zisserman, Andrew},
  booktitle = {CVPR},
  year = {2024},
  url = {https://arxiv.org/abs/2312.17247}
}

@inproceedings{pmlr-v270-long25b,
  title = {InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment},
  author = {Long, Yuxing and Cai, Wenzhe and Wang, Hongcheng and Zhan, Guanqi and Dong, Hao},
  booktitle = {Proceedings of The 8th Conference on Robot Learning},
  pages = {2049--2060},
  year = {2025},
  volume = {270},
  series = {Proceedings of Machine Learning Research},
  publisher = {PMLR},
  url = {https://proceedings.mlr.press/v270/long25b.html}
}

@inproceedings{clutter2024,
  title = {Broadcasting Support Relations Recursively from Local Dynamics for Object Retrieval in Clutters},
  author = {Li, Yitong and Wu, Ruihai and Lu, Haoran and Ning, Chuanruo and Shen, Yan and Zhan, Guanqi and Dong, Hao},
  booktitle = {Robotics: Science and Systems},
  year = {2024},
  url = {https://arxiv.org/abs/2406.02283}
}

@inproceedings{env2023,
  title = {Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusions},
  author = {Wu, Ruihai and Cheng, Kai and Shen, Yan and Ning, Chuanruo and Zhan, Guanqi and Dong, Hao},
  booktitle = {NeurIPS},
  year = {2023},
  url = {https://arxiv.org/abs/2309.07510}
}

@inproceedings{score2023,
  title = {Score-PA: Score-based 3D Part Assembly},
  author = {Cheng, Junfeng and Wu, Mingdong and Zhang, Ruiyuan and Zhan, Guanqi and Wu, Chao and Dong, Hao},
  booktitle = {BMVC},
  year = {2023},
  url = {https://arxiv.org/abs/2309.04220}
}

@inproceedings{tri2022,
  title = {A Tri-Layer Plugin to Improve Occluded Detection},
  author = {Zhan, Guanqi and Xie, Weidi and Zisserman, Andrew},
  booktitle = {BMVC},
  year = {2022},
  url = {https://arxiv.org/abs/2210.10046}
}

@inproceedings{dgl2020,
  title = {Generative 3D Part Assembly via Dynamic Graph Learning},
  author = {Huang, Jialei and Zhan, Guanqi and Fan, Qingnan and Mo, Kaichun and Shao, Lin and Chen, Baoquan and Guibas, Leonidas and Dong, Hao},
  booktitle = {NeurIPS},
  year = {2020},
  url = {https://arxiv.org/abs/2006.07793}
}

@article{dlgan2019,
  title = {DLGAN: Disentangling Label-Specific Fine-Grained Features for Image Manipulation},
  author = {Zhan, Guanqi and Zhao, Yihao and Zhao, Bingchan and Yuan, Haoqi and Chen, Baoquan and Dong, Hao},
  journal = {arXiv preprint arXiv:1911.09943},
  year = {2019},
  url = {https://arxiv.org/abs/1911.09943}
}