Yuanyuan Liu

刘圆圆

Postdoctoral Researcher

Cardiff University

Email: Liuyy990415@gmail.com

Biography

I am currently a Postdoctoral Researcher at Cardiff University, working with Prof. Yu-Kun Lai. I received my Ph.D. from Dalian University of Technology, where I was supervised by Prof. Xin Yang and co-supervised by Bo Dong.

Research Interests

My research focuses on advancing multimodal reasoning through graph structures. I investigate how graphs can connect information across modalities and enable models to reason over the relationships within these structured representations. In particular, I explore how these structures can guide models to retrieve relevant evidence and progressively refine their understanding. By explicitly connecting otherwise fragmented information, my research aims to make multimodal reasoning more reliable and interpretable, supporting decision-making in complex environments for applications such as embodied AI.

News!

2026.06: Got my Ph.D. degree from DUT and please call me Dr. Liu !
2025.11: One paper was accepted by AAAI 2026 !
2023.12: One paper was accepted by TVCG !
2022.01: One paper was accepted by TCSVT !
2020.02: One paper was accepted by CVPR 2020 !

Publications [ Google Scholar | ORCID | OpenReview ]

1.		View-on-Graph: Zero-Shot 3D Visual Grounding via Vision-Language Reasoning on Scene Graphs Yuanyuan Liu, Haiyang Mei, Dongyang Zhan, Jiayue Zhao, Dongsheng Zhou, Bo Dong, Xin Yang. The 40th Annual AAAI Conference on Artificial Intelligence (AAAI) 2026 [ PDF \| arXiv \| Project Page ]
2.		Explore Contextual Information for 3D Scene Graph Generation Yuanyuan Liu, Chengjiang Long, Zhaoxuan Zhang, Bokai Liu, Qiang Zhang, Baocai Yin, Xin Yang. IEEE Transactions on Visualization and Computer Graphics (TVCG) 2023 [ PDF \| arXiv \| Project Page ]
3.		Exploring Dense Context for Salient Object Detection Haiyang Mei, Yuanyuan Liu, Ziqi Wei, Dongsheng Zhou, Xiaopeng Wei, Qiang Zhang, Xin Yang. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) 2022 [ PDF \| Project Page ]
4.		Don't Hit Me! Glass Detection in Real-World Scenes Haiyang Mei, Xin Yang, Yang Wang, Yuanyuan Liu, Shengfeng He, Qiang Zhang, Xiaopeng Wei, Rynson W.H. Lau. The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020 [ PDF \| Project Page ]
5.		DCPNet: a comprehensive framework for multimodal sarcasm detection via graph topology extraction and multi-scale feature fusion Youjiang Fang, Liang Zhang, Shihao Wang, Wenyuan Zhang, Yuxin Wang, Yuanyuan Liu, Xiaopeng Wei, Xin Yang. Frontiers of Computer Science 2025 [ PDF ]
6.		Geometry hypergraph aware 3D scene graph generation Yuanyuan Liu, Youjiang Fang, Tianyu Meng, Zhengyu Meng, Pengwei Luo, Peigen Yang, Yutong Jiang, Xiaopeng Wei, Qiang Zhang, Xin Yang. Journal of Graphics 2025 [ PDF ]