Publications

2025

1. MMM 2025

   Understanding the Roles of Visual Modality in Multimodal Dialogue: An Empirical Study

   Qian Cao, Ruihua Song, and Xu Chen

   In Proceedings of the 31st International Conference on Multimedia Modeling, 2025, Jan 2025

   Bib PDF

   @inproceedings{Cao2024BSharedRAG,
     title = {Understanding the Roles of Visual Modality in Multimodal Dialogue: An Empirical Study},
     author = {Cao, Qian and Song, Ruihua and Chen, Xu},
     booktitle = {Proceedings of the 31st International Conference on Multimedia Modeling, 2025,},
     year = {2025},
     month = jan,
     doi = {10.1007/978-981-96-2071-5_20},
   }

2024

1. EMNLP 2024

   BSharedRAG: Backbone Shared Retrieval-Augmented Generation for the E-commerce Domain

   Kaisi Guan, Qian Cao, Yuchong Sun, Xiting Wang, and Ruihua Song

   In Findings of the Association for Computational Linguistics: EMNLP 2024, Nov 2024

   Bib arXiv PDF Overview Project Page

   

   @inproceedings{Guan2024BSharedRAG,
     title = {BSharedRAG: Backbone Shared Retrieval-Augmented Generation for the E-commerce Domain},
     author = {Guan, Kaisi and Cao, Qian and Sun, Yuchong and Wang, Xiting and Song, Ruihua},
     booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2024,},
     year = {2024},
     month = nov,
     doi = {10.18653/v1/2024.findings-emnlp.62},
   }

2. ACM MM 2024

   See or Guess: Counterfactually Regularized Image Captioning

   Qian Cao, Xu Chen, Ruihua Song, Xiting Wang, Xinting Huang, and Yuchen Ren

   In Proceedings of the 32th ACM international conference on Multimedia, Oct 2024

   Bib arXiv PDF Overview

   

   @inproceedings{Cao2024SeeOrGuess,
     title = {See or Guess: Counterfactually Regularized Image Captioning},
     author = {Cao, Qian and Chen, Xu and Song, Ruihua and Wang, Xiting and Huang, Xinting and Ren, Yuchen},
     booktitle = {Proceedings of the 32th ACM international conference on Multimedia,},
     year = {2024},
     month = oct,
     doi = {10.1145/3664647.3681458},
   }

3. arXiv

   YuLan: An Open-source Large Language Model

   Yutao Zhu, Kun Zhou, Kelong Mao, Wentong Chen, Yiding Sun, Zhipeng Chen, Qian Cao, Yihan Wu, Yushuo Chen, Feng Wang, and  others

   arXiv preprint arXiv:2406.19853 Oct 2024

   Bib arXiv PDF

   @article{zhu2024yulan,
     title = {YuLan: An Open-source Large Language Model},
     author = {Zhu, Yutao and Zhou, Kun and Mao, Kelong and Chen, Wentong and Sun, Yiding and Chen, Zhipeng and Cao, Qian and Wu, Yihan and Chen, Yushuo and Wang, Feng and others},
     journal = {arXiv preprint arXiv:2406.19853},
     year = {2024},
   }

2022

1. ACM MM 2022

   Multi-Modal Experience Inspired AI Creation

   Qian Cao, Xu Chen, Ruihua Song, Hao Jiang, Guang Yang, and Zhao Cao

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

   Bib arXiv PDF Overview

   

   @inproceedings{Cao2022MultiModalEI,
     title = {Multi-Modal Experience Inspired AI Creation},
     author = {Cao, Qian and Chen, Xu and Song, Ruihua and Jiang, Hao and Yang, Guang and Cao, Zhao},
     booktitle = {Proceedings of the 30th ACM international conference on Multimedia,},
     year = {2022},
     month = oct,
     doi = {10.1145/3503161.3548189},
   }