@inproceedings{li2027dcsnet,
  title = {Mitigating Prior Shape Bias in Point Clouds via Differentiable Center Learning},
  author = {Zhe Li and Xiying Wang and Jinglin Zhao and Zheng Wang and Debin Liu and Laurence T. Yang},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
  year = {2027},
  note = {Accepted},
  eprint = {2402.02088},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2402.02088}
}

@inproceedings{li2026robodreamer,
  title = {RoboDreamer: Anticipatory Humanoid Locomotion with Predictive State-Space Models},
  author = {Zhe Li and Yangyang Wei and Xichen Yuan and Zhenzhe Zhang and Weihao Yuan and Shanghang Zhang and Jianfei Yang},
  booktitle = {Conference on Robot Learning (CoRL)},
  year = {2026},
  eprint = {2609.07096},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/pdf/2609.07096}
}

@article{bai2026unifiedrobotmanipulation,
  title = {Towards a Unified Understanding of Robot Manipulation: A Comprehensive Survey},
  author = {Shuanghao Bai and Wenxuan Song and Jiayi Chen and Yuheng Ji and Zhide Zhong and Jin Yang and Han Zhao and Wanqi Zhou and Wei Zhao and Zhe Li and Pengxiang Ding and Cheng Chi and Haoang Li and Chang Xu and Xiaolong Zheng and Donglin Wang and Shanghang Zhang and Badong Chen},
  journal = {IEEE Transactions on Robotics},
  year = {2026},
  note = {Accepted},
  eprint = {2510.10903},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2510.10903}
}

@misc{li2026omega0latentpredictiveworld,
  title = {{ω-0}: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation},
  author = {Zhe Li and Zhenzhe Zhang and Yangyang Wei and Wenjie Zhang and Xichen Yuan and Peiyuan Zhi and Gen Li and Xinying Guo and Fengjie Gao and Jianfei Yang and Shanghang Zhang},
  year = {2026},
  eprint = {2608.06375},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2608.06375}
}

@article{li2024mulsmo,
  title = {{MulSMo}: Multimodal Stylized Motion Generation by Bidirectional Control Flow},
  author = {Zhe Li and Y He and L Zhong and W Shen and Q Zuo and L Qiu and Z Dong and Laurence T. Yang and W Yuan},
  year = {2026},
  journal = {IEEE Transactions on Image Processing},
  url = {https://arxiv.org/abs/2412.09901}
}

@misc{shan2026learningphysicalinteractionsurvey,
  title = {Learning Physical Interaction: A Survey of Tactile- and Force-aware Robot Learning},
  author = {Shilin Shan and Chuhao Zhou and Ruize Wang and Xinyan Chen and Xiangyu Chen and Xinyu Zhou and Boyu Ma and Iris Yuxuan Hu and Jingliang Li and Celeste Yuxuan Hu and Geng Li and Guohao Chen and Tianrui Zhu and Zhe Li and Yanjie Ze and Haoran Geng and Zhiyang Dou and Jianxin Bi and Yuejiang Liu and Jianshu Zhou and Jiachen Li and Paul Liang and Tatsuya Harada and Robert Katzschmann and Harold Soh and Na Li and Edward Johns and Danica Kragic and Jan Peters and Wojciech Matusik and Masayoshi Tomizuka and Jitendra Malik and Jianfei Yang},
  year = {2026},
  eprint = {2608.07558},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2608.07558}
}

@misc{yuan2026roboforge,
  title = {{RoboForge}: Physically Optimized Text-guided Whole-Body Locomotion for Humanoids},
  author = {X Yuan and Zhe Li and B Lyu and K Zuo and Y Lu and G Li and J Yang},
  year = {2026},
  journal = {arXiv preprint arXiv:2603.17927},
  url = {https://arxiv.org/abs/2603.17927}
}

@misc{sun2026mosaic,
  title = {{Mosaic}: Bridging the Sim-to-Real Gap in Generalist Humanoid Motion Tracking and Teleoperation with Rapid Residual Adaptation},
  author = {Z Sun and BS Huang and Y Peng and X Li and J Ma and Y Sun and Zhe Li and H Jiang and B Gao and Z Bing},
  year = {2026},
  journal = {arXiv preprint arXiv:2602.08594},
  url = {https://arxiv.org/abs/2602.08594}
}

@misc{bai2026latentvla,
  title = {Latent Reasoning {VLA}: Latent Thinking and Prediction for Vision-Language-Action Models},
  author = {S Bai and J Lyu and W Zhou and Zhe Li and D Wang and L Xing and X Zhao and P Wang and Z Wang},
  year = {2026},
  journal = {arXiv preprint arXiv:2602.01166},
  url = {https://arxiv.org/abs/2602.01166}
}

@misc{tan2026robobrain,
  title = {{RoboBrain} 2.5: Depth in Sight, Time in Mind},
  author = {H Tan and E Zhou and Zhe Li and Y Xu and Y Ji and X Chen and C Chi and P Wang and H Jia and Y Ao},
  year = {2026},
  journal = {arXiv preprint arXiv:2601.14352},
  url = {https://arxiv.org/abs/2601.14352}
}

@inproceedings{li2025robomirror,
  title = {{RoboMirror}: Understand Before You Imitate for Video to Humanoid Locomotion},
  author = {Zhe Li and C Chi and B Zhu and Y Wei and S Bai and Y Ji and Y Peng and T Huang and P Wang and Z Wang},
  year = {2026},
  booktitle = {European Conference on Computer Vision (ECCV)},
  url = {https://arxiv.org/abs/2512.23649}
}

@inproceedings{li2026freestyle,
  title = {Do You Have Freestyle? Expressive Humanoid Locomotion via Audio Control},
  author = {Zhe Li and Cheng Chi and Yangyang Wei and Boan Zhu and Tao Huang and Zhenguo Sun and Yibo Peng and Pengwei Wang and Zhongyuan Wang and Fangzhou Liu and Chang Xu and Shanghang Zhang},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  note = {Highlight},
  url = {https://arxiv.org/abs/2512.23650}
}

@inproceedings{li2026language2loco,
  title = {From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance},
  author = {Zhe Li and Yangyang Wei and Boan Zhu and Yibo Peng and Tao Huang and Pengwei Wang and Zhongyuan Wang and Cheng Chi and Shanghang Zhang and Chang Xu},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://arxiv.org/abs/2510.14952}
}

@misc{bai2025embodiedsurvey,
  title = {Embodied Robot Manipulation in the Era of Foundation Models: Planning and Learning Perspectives},
  author = {S Bai and W Song and J Chen and Y Ji and Z Zhong and J Yang and H Zhao and W Zhou and Zhe Li},
  year = {2025},
  journal = {arXiv preprint arXiv:2512.22983},
  url = {https://arxiv.org/abs/2512.22983}
}

@misc{li2025omnimotion,
  title = {{OmniMotion}: Multimodal Motion Generation with Continuous Masked Autoregression},
  author = {Zhe Li and Weihao Yuan and Weichao Shen and Siyu Zhu and Zilong Dong and Chang Xu},
  year = {2025},
  journal = {arXiv preprint arXiv:2510.14954},
  url = {https://arxiv.org/abs/2510.14954}
}

@inproceedings{qiu2025anigs,
  title = {{ANIgs}: Animatable {G}aussian Avatar from a Single Image with Inconsistent {G}aussian Reconstruction},
  author = {L Qiu and S Zhu and Q Zuo and X Gu and Y Dong and J Zhang and C Xu and Zhe Li and W Yuan and L Bo},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://arxiv.org/abs/2412.02684}
}

@inproceedings{li2025lamp,
  title = {{LaMP}: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning},
  author = {Zhe Li and Weihao Yuan and Yisheng He and Lingteng Qiu and Shenhao Zhu and X Gu and Weichao Shen and Y Dong and Zilong Dong},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://arxiv.org/abs/2410.07093}
}

@misc{zhu2024mcmat,
  title = {{MCMat}: Multiview-consistent and Physically Accurate {PBR} Material Generation},
  author = {S Zhu and L Qiu and X Gu and Z Zhao and C Xu and Y He and Zhe Li and X Han and Y Yao and X Cao and S Zhu},
  year = {2024},
  journal = {arXiv preprint arXiv:2412.14148},
  url = {https://arxiv.org/abs/2412.14148}
}

@inproceedings{li2024gpm,
  title = {General Point Model Pretraining with Autoencoding and Autoregressive},
  author = {Zhe Li and Zhangyang Gao and Cheng Tan and Bocheng Ren and Laurence T. Yang and Stan Z. Li},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  note = {Top Ten Outstanding Paper Award, HUST},
  url = {https://openaccess.thecvf.com/content/CVPR2024/papers/Li_General_Point_Model_Pretraining_with_Autoencoding_and_Autoregressive_CVPR_2024_paper.pdf}
}

@inproceedings{li2024mlip,
  title = {{MLIP}: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning},
  author = {Zhe Li and Laurence T. Yang and Bocheng Ren and Xin Nie and Zhangyang Gao and Cheng Tan and Stan Z. Li},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://openaccess.thecvf.com/content/CVPR2024/papers/Li_MLIP_Enhancing_Medical_Visual_Representation_with_Divergence_Encoder_and_Knowledge-guided_CVPR_2024_paper.pdf}
}

@inproceedings{li2023acmmm,
  title = {Enhancing Sentence Representation with Visually-supervised Multimodal Pre-training},
  author = {Zhe Li and Laurence T. Yang and Xin Nie and Bocheng Ren and Xianjun Deng},
  booktitle = {ACM International Conference on Multimedia (ACM MM)},
  year = {2023},
  url = {https://doi.org/10.1145/3581783.3612254}
}