Hi! I’m a third year Ph.D. Candidate from Institute of Information Engineering,Chinese Academy of Sciences. I am very fortunate to be advised by Prof. Hongbo Xu and Prof. Yongxiu Xu. I’ve also interned at Xiaomi Corporation.
My research interest includes Multimodal Knowledge Graph, Retrieval-Augmented Generation, and Information Retrieval and Extraction. I am expected to complete my Ph.D. in June 2028, and will be actively seeking opportunities in both industry and academia. If you are interested, please feel free to get in touch.
🔥 News
- 2025.11: 🎉 Our paper “From Agnostic to Specific: Latent Preference Diffusion for Multi-Behavior Sequential Recommendation” has been accepted by KDD 2026 (CCF-A)!
- 2025.08: 🎉 Our paper “MAKAR: a Multi-Agent framework based Knowledge-Augmented Reasoning for Grounded Multimodal Named Entity Recognition” has been accepted by EMNLP 2025 (CCF-B)!
- 2025.07: 🎉 Our paper “REMOTE: A Unified Multimodal Relation Extraction Framework with Multilevel Optimal Transport and Mixture-of-Experts” has been accepted by ACM MM 2025 (CCF-A)!
- 2025.07: 🎉 Our paper “An Adaptive Semantic-Aware Fusion Method for Multimodal Entity Linking” has been accepted by NLPCC 2025 (CCF-C)!
- 2025.06: 🎉 Our paper “RDA: Regularized Domain Adaptation for Multimedia Event Extraction” has been accepted by ICIC 2025 (CCF-C)!
- 2025.04: 🎉 Our paper “EilMoB: Emotion-aware Incongruity Learning and Modality Bridging Network for Multi-modal Sarcasm Detection” has been accepted by ICMR 2025 (CCF-B)!
📝 Publications
-
From Agnostic to Specific: Latent Preference Diffusion for Multi-Behavior Sequential Recommendation. Ruochen Yang, Xiaodong Li, Jiawei Sheng, Jiangxia Cao, Xinkui Lin, Shen Wang, yangshuang, Liu Zhaojie, Tingwen Liu. 32nd SIGKDD Conference on Knowledge Discovery and Data Mining, 2026 (KDD 2026).
-
MAKAR: a Multi-Agent framework based Knowledge-Augmented Reasoning for Grounded Multimodal Named Entity Recognition. Xinkui Lin, yuhui zhang, Yongxiu Xu, Kun Huang, Hongzhang Mu, Yubin Wang, Gaopeng Gou, Li Qian, Li Peng, Wei Liu, Jian Luan, Hongbo Xu. The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025).
-
REMOTE: A Unified Multimodal Relation Extraction Framework with Multilevel Optimal Transport and Mixture-of-Experts. Xinkui Lin, Yongxiu Xu, Minghao Tang, Shilong Zhang, Hongbo Xu, Hao Xu, Yubin Wang. Proceedings of the 33rd ACM International Conference on Multimedia (MM ‘25).
-
An Adaptive Semantic-Aware Fusion Method for Multimodal Entity Linking. Hao Xu, Yongxiu Xu, Xinkui Lin, Hongbo Xu, Yubin Wang, Gaopeng Gou. The 14th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC 2025).
-
RDA: Regularized Domain Adaptation for Multimedia Event Extraction. Yuhui Zhang, Yongxiu Xu, Minghao Tang, Xinkui Lin, Yubin Wang, Hongbo xu, Gaopeng Gou. 21st International Conference on Intelligent Computing (ICIC 2025).
-
EilMoB: Emotion-aware Incongruity Learning and Modality Bridging Network for Multi-modal Sarcasm Detection. Haochen Zhao, Yongxiu Xu, Xinkui Lin, Jiarui Lu, Hongbo Xu, and Yubin Wang. 2025. Proceedings of the 2025 International Conference on Multimedia Retrieval (ICMR ‘25).
🎖 Honors and Awards
- 2025.03 Merit Student of University of Chinese Academy of Sciences
- 2024.09 Best Demo Award, CCKS-IJCKG 2025
- 2019.09~2022.09 Merit Student of University of Electronic Science and Technology of China
📖 Educations
- 2023.09 - Present, Ph.D. Candidate, Cyberspace Security, Chinese Academy of Sciences
- 2019.09 - 2023.06, Undergraduate, Computer Science and Technology, University of Electronic Science and Technology of China
⭐ Services
- Program Committee / Reviewer: ICME 2024, PRICAI 2025
- Secondary Reviewer: ACL 2024-2025, AAAI 2025-2026, SIGIR 2024-2025, EMNLP 2025, WSDM 2026
💻 Internships
Xiaomi Inc, focusing on Multi-Modal Retrieval-Augmented Generation