publications

2025

1. ICLR

   AnyPrefer: An Agentic Framework for Preference Data Synthesis

   Yiyang Zhou, Zhaoyang Wang, Tianle Wang, Shangyu Xing, and 12 more authors

   In International Conference on Learning Representations, 2025

   arXiv Bib

   @inproceedings{zhou2024anyprefer,
     title = {AnyPrefer: An Agentic Framework for Preference Data Synthesis},
     author = {Zhou, Yiyang and Wang, Zhaoyang and Wang, Tianle and Xing, Shangyu and Xia, Peng and Li, Bo and Zheng, Kaiyuan and Zhang, Zijian and Chen, Zhaorun and Zheng, Wenhao and Zhang, Xuchao and Bansal, Chetan and Zhang, Weitong and Wei, Ying and Bansal, Mohit and Yao, Huaxiu},
     booktitle = {International Conference on Learning Representations},
     year = {2025},
   }

2. preprint

   GePBench: Evaluating Fundamental Geometric Perception for Multimodal Large Language Models

   Shangyu Xing, Changhao Xiang, Yuteng Han, Yifan Yue, and 5 more authors

   submitted to NeurIPS 2025, 2025

   arXiv Bib Slides

   @article{xing2024gepbenchevaluatingfundamentalgeometric,
     title = {GePBench: Evaluating Fundamental Geometric Perception for Multimodal Large Language Models},
     author = {Xing, Shangyu and Xiang, Changhao and Han, Yuteng and Yue, Yifan and Wu, Zhen and Liu, Xinyu and Wu, Zhangtai and Zhao, Fei and Dai, Xinyu},
     year = {2025},
     journal = {submitted to NeurIPS 2025},
   }

3. ACL

   Maximizing the Effectiveness of Larger BERT Models for Compression

   Wenshu Fan, Su Lu, Shangyu Xing, Xinchun Li, and 1 more author

   ACL 2025, 2025
4. preprint

   RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios

   Fei Zhao, Chengqiang Lu, Yufan Shen, Qimeng Wang, and 8 more authors

   submitted to EMNLP 2025, 2025

2024

1. EMNLP

   EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models

   Shangyu Xing, Fei Zhao, Zhen Wu, Tuo An, and 4 more authors

   EMNLP 2024, 2024

   arXiv Bib Code

   @article{xing2024efuf,
     title = {EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models},
     author = {Xing, Shangyu and Zhao, Fei and Wu, Zhen and An, Tuo and Chen, Weihao and Li, Chunhui and Zhang, Jianbing and Dai, Xinyu},
     journal = {EMNLP 2024},
     year = {2024},
   }

2. preprint

   AlignGPT: Multi-modal Large Language Models with Adaptive Alignment Capability

   Fei Zhao, Taotian Pang, Chunhui Li, Zhen Wu, and 3 more authors

   submitted to EMNLP 2025, 2024

   arXiv Bib Code

   @article{zhao2024aligngpt,
     title = {AlignGPT: Multi-modal Large Language Models with Adaptive Alignment Capability},
     author = {Zhao, Fei and Pang, Taotian and Li, Chunhui and Wu, Zhen and Guo, Junjie and Xing, Shangyu and Dai, Xinyu},
     journal = {submitted to EMNLP 2025},
     year = {2024},
   }

2023

1. ACMMM

   DRIN: Dynamic Relation Interactive Network for Multimodal Entity Linking

   Shangyu Xing^*, Fei Zhao^*, Zhen Wu, Chunhui Li, and 2 more authors

   In Proceedings of the 31st ACM International Conference on Multimedia, 2023

   arXiv Bib Code

   @inproceedings{xing2023drin,
     title = {DRIN: Dynamic Relation Interactive Network for Multimodal Entity Linking},
     author = {Xing, Shangyu and Zhao, Fei and Wu, Zhen and Li, Chunhui and Zhang, Jianbing and Dai, Xinyu},
     booktitle = {Proceedings of the 31st ACM International Conference on Multimedia},
     pages = {3599--3608},
     year = {2023},
   }

2022

1. ACMMM

   Learning from different text-image pairs: a relation-enhanced graph convolutional network for multimodal NER

   Fei Zhao, Chunhui Li, Zhen Wu, Shangyu Xing, and 1 more author

   In Proceedings of the 30th ACM international conference on multimedia, 2022

   Bib Code Website

   @inproceedings{zhao2022learning,
     title = {Learning from different text-image pairs: a relation-enhanced graph convolutional network for multimodal NER},
     author = {Zhao, Fei and Li, Chunhui and Wu, Zhen and Xing, Shangyu and Dai, Xinyu},
     booktitle = {Proceedings of the 30th ACM international conference on multimedia},
     pages = {3983--3992},
     year = {2022},
   }