Qiyao Xue

US, Pennsylvania, Pittsburgh

Hi! I’m Qiyao Xue, currently a first year PhD student in the Department of Electrical and Computer Engineering at the University of Pittsburgh advised by Prof Wei Gao. Before that, I obtained by bachelor degree with first class honor at Hong Kong Polytechnic University major in Electrical Engineering and minor in Applied Mathematics.

My research interest lies in multimodal generative AI, bridging language, vision, and audio that move toward world models capable of perceiving, reasoning, and generating across modalities.

In the past, I worked on deep learning, computer vision and natural language processing. I’m fortunate to had the opportunities to collaborate with Prof Xiang Lorraine Li on natural language processing, Prof Qi Dou on medical image analysis.

Contact: 19083647d AT connect.polyu.hk

news

Aug 01, 2025	New perprint: MMBERT: Scaled Mixture-of-Experts Multimodal BERT for Robust Chinese Hate Speech Detection under Cloaking Perturbations
Jul 30, 2025	Paper accpeted to ICCV’25 highlight poster: ProGait: A Multi-Purpose Video Dataset and Benchmark for Transfemoral Prosthesis Users
Jul 14, 2025	New perprint: ProGait: A Multi-Purpose Video Dataset and Benchmark for Transfemoral Prosthesis Users
Mar 30, 2025	Paper accpeted to CVPR’25 poster: PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation
Nov 30, 2024	New perprint: PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation

selected publications

CVPR

Phyt2v: Llm-guided iterative self-refinement for physics-grounded text-to-video generation

Qiyao Xue, Xiangyu Yin, Boyuan Yang, and 1 more author

In Proceedings of the Computer Vision and Pattern Recognition Conference, 2025

DOI Bib Poster

@inproceedings{xue2025phyt2v,
  title = {Phyt2v: Llm-guided iterative self-refinement for physics-grounded text-to-video generation},
  author = {Xue, Qiyao and Yin, Xiangyu and Yang, Boyuan and Gao, Wei},
  booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference},
  pages = {18826--18836},
  year = {2025},
  doi = {10.48550/arXiv.2412.00596},
  publisher = {CVPR},
  selected = true
}

ICCV (Highlight)

ProGait: A Multi-Purpose Video Dataset and Benchmark for Transfemoral Prosthesis Users

Xiangyu Yin, Boyuan Yang, Weichen Liu, and 4 more authors

In Proceedings of the International Conference on Computer Vision, 2025

DOI Bib

@inproceedings{yin2025progait,
  title = {ProGait: A Multi-Purpose Video Dataset and Benchmark for Transfemoral Prosthesis Users},
  author = {Yin, Xiangyu and Yang, Boyuan and Liu, Weichen and Xue, Qiyao and Alamri, Abrar and Fiedler, Goeran and Gao, Wei},
  booktitle = {Proceedings of the International Conference on Computer Vision},
  year = {2025},
  doi = {10.48550/arXiv.2507.10223},
  publisher = {ICCV},
  selected = true
}