Dr Yingfang Yuan

Lecturer

School: Computer Science

Yingfang received his doctoral degree in Computer Science from Heriot-Watt University and his master’s degree in Big Data and High-Performance Computing from the University of Liverpool. His research interests include AI agents, multi-agent systems, inter- and multidisciplinary AI, graph neural networks, and multimodal large language models. He has published papers at prestigious international conferences, including CVPR, ICML, AAAI, ECCV, NeurIPS, EMNLP, IJCNN, GECCO, and The Web Conference.

Email Yingfang

Key Publications

Please visit the Pure Research Information Portal for further information
SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration, Yang, Z., Yang, Z., Zhan, S., Yue, T., Pang, W., Yuan, Y. 6 Apr 2026, The Computer Vision and Pattern Recognition Conference, Piscataway, NJ, IEEE
Do Vision and Text Cues Exhibit Evidential Coupling? UFO: A Benchmark for Compositional Multimodal Reasoning in Unified Models, Yang, Z., Xu, D., Zhang, Y., Chen, K., Wang, X., Xu, Y., Pang, W., Yuan, Y. 30 Apr 2026, In: Proceedings of Machine Learning Research
InEx: Hallucination Mitigation via Introspection and Cross-Modal Multi-Agent Collaboration, Yang, Z., Yuan, Y., Jiang, X., An, B., Pang, W. 14 Mar 2026, Proceedings of the AAAI Conference on Artificial Intelligence, Singapore, Association for the Advancement of Artificial Intelligence (AAAI)
MultiHaystack: Benchmarking Multimodal Retrieval and Reasoning over 40K Images, Videos, and Documents, Xu, D., Yang, Z., Chen, J., Yuan, Y., Hu, M., Sun, L., Van Gool, L., Paudel, D., Feng, C. 22 Sep 2026, Computer Vision – ECCV 2026, Cham, Switzerland, Springer
FACE: Evaluating Natural Language Generation with Fourier Analysis of Cross-Entropy, Yang, Z., Yuan, Y., Xu, Y., Zhan, S., Bai, H., Chen, K. 16 Dec 2023, Advances in Neural Information Processing Systems 36, Neural Information Processing Systems Foundation
MERMAID: Multi-perspective Self-reflective Agents with Generative Augmentation for Emotion Recognition, Yang, Z., Song, J., Song, S., Pang, W., Yuan, Y. 1 Nov 2025, Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Kerrville, TX, Association for Computational Linguistics
OpenAqua: An automated multi-agent framework for early-stage water treatment train design with retrieval augmentation and critic-based refinement, Liu, H., Jiang, Z., Zhong, H., Li, J., Pang, W., Yuan, Y. 28 Aug 2026, In: Water Research
XR: Cross-Modal Agents for Composed Image Retrieval, Yang, Z., Pang, W., Yuan, Y. 12 Apr 2026, WWW '26: Proceedings of the ACM Web Conference 202, New York, NY, United States, ACM
Script: Graph-Structured and Query-Conditioned Semantic Token Pruning for Multimodal Large Language Models, Yang, Z., Xu, D., Pang, W., Yuan, Y. 22 Nov 2025, In: Transactions on Machine Learning Research
Conversational Human Audio-visual Talking Dialogue Generation, Song, J., Guasch, ., He, X., Yang, Z., Yuan, Y., Xie, W., Shen, L., Lin, H., Liu, S., Pang, W., Song, S. 10 Sep 2026, Computer Vision – ECCV 2026, Cham, Switzerland, Springer