Haiyang Guo

I'm currently a first-year Ph.D. student at School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, enrolled in the integrated M.S.-Ph.D. program, supervised by Prof. Xu-Yao Zhang and Prof. Cheng-Lin Liu. I previously studied at the Institute of Automation, Chinese Academy of Sciences, under the same supervision.

Before that, I obtained my Bachlor degree from University of Science and Technology Beijing, majoring in Artificial Intelligence.

My research focuses on continual learning for real-world applications, with an emphasis on multimodal continual learning and federated continual learning. I am also interested in other downstream tasks of MLLMs, including memory systems, model merging, and hallucination mitigation.

Email / Google Scholar / Github

Education

Ph.D. @ SAIS, University of Chinese Academy of Sciences, 2025.02 - 2028.06 (expected)
Advisor: Prof. Xu-Yao Zhang and Prof. Cheng-Lin Liu
M.S. @ MAIS, Institute of Automation, Chinese Academy of Sciences, 2023.09 - 2025.02
Advisor: Prof. Xu-Yao Zhang and Prof. Cheng-Lin Liu
B.E. @ SIST, University of Science and Technology Beijing, 2019.09 - 2023.06

News

[2025.08] One paper (ModalPrompt) is accepted to EMNLP 2025. Congratulations to all my collaborators!
[2025.06] One paper (FCIT) is accepted to ICCV 2025.
[2025.05] One papers (HiDe-LLaVA) is accepted to ACL 2025.
[2024.07] One paper (PILoRA) is accepted to ECCV 2024.

Publications

* indicates equal contribution

	ModalPrompt: Dual-Modality Guided Prompt for Continual Learning of Large Multimodal Models Fanhu Zeng, Fei Zhu, Haiyang Guo, Xu-Yao Zhang, Cheng-Lin Liu Empirical Methods in Natural Language Processing (EMNLP), 2025 arXiv / Code
	Federated Continual Instruction Tuning Haiyang Guo, Fanhu Zeng, Fei Zhu, Wenzhuo Liu, Da-Han Wang, Jian Xu, Xu-Yao Zhang, Cheng-Lin Liu International Conference on Computer Vision (ICCV), 2025 arXiv / Code
	HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Language Model Haiyang Guo, Fanhu Zeng, Ziwei Xiang, Fei Zhu, Da-Han Wang, Xu-Yao Zhang, Cheng-Lin Liu Association for Computational Linguistics (ACL), 2025 Paper / arXiv / Code
	PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learning Haiyang Guo, Fei Zhu, Wenzhuo Liu, Xu-Yao Zhang, Cheng-Lin Liu European Conference on Computer Vision (ECCV), 2024 Paper / arXiv / Code

Preprints

	LLaVA-c: Continual Improved Visual Instruction Tuning Wenzhuo Liu, Fei Zhu, Haiyang Guo, Longhui Wei, Cheng-Lin Liu arXiv
	A Comprehensive Survey on Continual Learning in Generative Models Haiyang Guo, Fanhu Zeng, Fei Zhu, Jiayi Wang, Xukai Wang, Jingang Zhou, Hongbo Zhao, Wenzhuo Liu, Shijie Ma, Da-Han Wang, Xu-Yao Zhang, Cheng-Lin Liu arXiv / Code
	Parameter Efficient Merging for Multimodal Large Language Models with Complementary Parameter Adaptation Fanhu Zeng, Haiyang Guo, Fei Zhu, Li Shen, Hao Tang arXiv
	Dynamic Knowledge Consolidation for Rehearsal-Free Continual Learning Haiyang Guo, Fei Zhu, Fanhu Zeng, Bing Liu, Xu-Yao Zhang arXiv

Website Template