I am a first-year doctoral student majoring in Computer Science and Technology at Shanghai Innovation Institute, OpenMOSS Team, under the supervision of Prof. Xipeng Qiu. And I am also a student at East China Normal University, School of Computer Science and Technology, under the supervision of Prof. Liang He and Prof. Jie Zhou. Currently, I focus on continual learning for agents and AI for research. I have also researched domain adaptation learning, semantic segmentation, and visual question answering.
I am seeking the collaboration of Continual Learning of LLMs. If you are also interested in Continual Learning, please feel free to communicate with me!
🔥 News
- 2025.02: Our paper on Continual Learning of Multi-modal Large Language Models is accepted by the CVPR2025. Released on arXiv.
- 2025.01: Our paper Efficiency is the rule on Domain Adaptive Semantic Segmentation is accepted to ESWA.
- 2024.01: Our paper on Debiased Visual Question Answering is accepted by PRL and released on here.
- 2023.03: Our paper SQT on VQA is accepeted by ICME2023 and released on here.
📝 Publications
CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering
Tianyu Huai, Jie Zhou*, Xingjiao Wu, Qin Chen, Qingchun Bai, Ze Zhou, Liang He. Preprint
(* Corresponding Author)
The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025 (Highlight paper, CCF-A, TOP🔥🔥🔥)
Efficiency is the rule: Domain adaptive semantic segmentation with minimal annotations
Tianyu Huai, Junhang Zhang, Xingjiao Wu*, Jian Jin, Liang He. ESWA
(* Corresponding Author)
Expert Systems with Applications (SCI-District 1, IF=7.5, TOP🔥🔥🔥)
Debiased visual question answering via the perspective of question types
Tianyu Huai, Shuwen Yang, Junhang Zhang, Jiabao Zhao*, Liang He. PRL
(* Corresponding Author)
Pattern Recognition Letters (SCI-District 3, IF=5.1)
Sqt: Debiased visual question answering via shuffling question types
Tianyu Huai, Shuwen Yang, Junhang Zhang, Guoan Wang, Xinru Yu, Tianlong Ma*, Liang He. ICME
(* Corresponding Author)
The IEEE International Conference on Multimedia and Expo 2023 (CCF-B)
-
Recent Advances of Foundation Language Models-based Continual Learning: A Survey, Yutao Yang, Jie Zhou, Xuanwen Ding, Tianyu Huai, Shunyu Liu, Qin Chen, Yuan Xie, Liang He.
-
Enhancing Out-of-Distribution Generalization in VQA through Gini Impurity-guided Adaptive Margin Loss, Shuwen Yang*, Tianyu Huai*, Anran Wu, Xingjiao Wu, Wenxin Hu, Liang He.
🎖 Honors and Awards
- 2020.10 The National Scholarship (Ministry of Education of the People’s Republic of China)
- 2020.11 The Second Prize in the 11th Blue Bridge Cup JAVA Group B National Competition (Ministry of Industry and Information Technology)
- 2019.10 The Special Prize in the 2nd Shandong University Student Artificial Intelligence Competition (Shandong Provincial Department of Education)
- 2020.11 The First Prize in the 11th Blue Bridge Cup JAVA Group B Provincial Competition (Ministry of Industry and Information Technology)
- 2020.07 Huawei Kunpeng HCIA Developer Certification
- 2022.06 Outstanding Graduate of Shandong Province (Shandong Provincial Department of Education)
- Several school-level awards (Principal’s Scholarship, Good Students, Outstanding Communist Party Members, Outstanding Student Leaders, etc.)
📖 Academic Services
- Journal Reviewer: ESWA, TMM