publications

2026

1. AAAI

   

   MMBERT: Scaled Mixture-of-Experts Multimodal BERT for Robust Chinese Hate Speech Detection under Cloaking Perturbations

   Qiyao Xue, Yuchen Dou, Ryan Shi, and 2 more authors

   In Annual AAAI Conference on Artificial Intelligence, 2026

   DOI Bib

   

   @inproceedings{xue2026mmbert,
     title = {MMBERT: Scaled Mixture-of-Experts Multimodal BERT for Robust Chinese Hate Speech Detection under Cloaking Perturbations},
     author = {Xue, Qiyao and Dou, Yuchen and Shi, Ryan and Li, Xiang Lorraine and Gao, Wei},
     booktitle = {Annual AAAI Conference on Artificial Intelligence},
     year = {2026},
     doi = {10.48550/arXiv.2508.00760},
     publisher = {AAAI},
     selected = true
   }

2. CVPR (Oral)

   

   InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity

   Haoming Wang, Qiyao Xue, and Wei Gao

   In Proceedings of the Computer Vision and Pattern Recognition Conference, 2026

   DOI Bib

   

   @inproceedings{xue2026infinigen,
     title = {InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity},
     author = {Wang, Haoming and Xue, Qiyao and Gao, Wei},
     booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference},
     year = {2026},
     doi = {10.48550/arXiv.2511.18200},
     publisher = {CVPR},
     selected = true
   }

2025

1. 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
   }

2. 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
   }