I am a Postdoctoral Fellow at the Hong Kong University of Science and Technology, supervised by Prof. Hao Chen. I received my Ph.D. from Sichuan University, where I was fortunate to be advised by Prof. Xi Peng.

My research mainly focuses on Multi-modal Learning and AI4Medical, with contributions in:

• i) Robust Multi-modal Self-supervised Learning: representation learning under modality missing (CVPR’21, TPAMI’22, ICLR’26) and noisy correspondence (ICCV’23, ICLR’24, ICLR’26, TPAMI’26) in visual-text and multi-angle data. For a comprehensive overview of insights on noisy correspondence, please refer to our repository Noisy Correspondence Summary.
• ii) Interactive and Agentic Multi-modal Learning: moving beyond passive perception toward interactive (ICML’25, LLaVA-ReID), tool-augmented (ICML’25, Visual Abstraction), and knowledge-grounded agents.
• iii) Medical AI for Breast Cancer, Computational Pathology, and Bioinformatics: representative cell selection (Nature Communications’25) and batch effect correction (TNNLS’23).

🔥 News

📝 Selected Publications

* Equal contribution ^† Corresponding author

[NeurIPS’26] ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge
Yijie Lin*, Guofeng Ding*, Haochen Zhou*, Haobin Li, Mouxing Yang, Xi Peng

中文简介 |

• A multimodal retrieval benchmark spanning knowledge domains and reasoning skills, beyond surface-level semantic similarity.

[ICML’25] LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification
Yiding Lu, Mouxing Yang, Dezhong Peng, Peng Hu, Yijie Lin^†, Xi Peng^†

中文简介 | Code | Poster

• Introduce the first dialogue-based person re-identification task.

[ICML’25] Visual Abstraction: A Plug-and-Play Approach for Text-Visual Retrieval
Guofeng Ding, Yiding Lu, Peng Hu, Mouxing Yang, Yijie Lin^†, Xi Peng^†

中文简介 | Code

• Transform visual content into textual descriptions in a training-free manner
• A generative question-answer paradigm to enhance discriminative retrieval

[ICLR’24] Multi-granularity Correspondence Learning from Long-term Noisy Videos
Yijie Lin, Jie Zhang, Zhenyu Huang, Jia Liu, Zujie Wen, Xi Peng

(Oral presentation, 1.2%) | 中文简介 | Slides | Poster | Code

• Reveal multi-granularity noisy correspondence in long-term temporal modeling.

• Propose an efficient and robust video-language pre-training method.

[CVPR’21] COMPLETER: Incomplete Multi-view Clustering via Contrastive Prediction
Yijie Lin, Yuanbiao Gou, Zitao Liu, Boyun Li, Jiancheng Lv, Xi Peng

中文简介 | Video | Code

[TPAMI’22] Dual Contrastive Prediction for Incomplete Multi-view Representation Learning
Yijie Lin, Yuanbiao Gou, Xiaotian Liu, Jinfeng Bai, Jiancheng Lv, Xi Peng

中文简介 | Code

[ICCV’23] Graph Matching with Bi-level Noisy Correspondence
Yijie Lin, Mouxing Yang, Jun Yu, Peng Hu, Changqing Zhang, Xi Peng

中文简介 | Video | Code

[TPAMI’26] Learning with Partial and Noisy Correspondence in Graph Matching
Yijie Lin, Mouxing Yang, Peng Hu, Jiancheng Lv, Hao Chen, Xi Peng

• Included by famous graph matching project ThinkMatch

[ICML’26] Reliable Thinking with Images
Haobin Li, Yutong Yang, Yijie Lin, Xiang Dai, Mouxing Yang, Xi Peng

中文简介 | Code

• Mitigate noisy visual cue mining and noisy reasoning in Thinking-with-Images.
• Demonstrates effectiveness across seven multimodal reasoning benchmarks.

• [ICLR’26] (Oral) Learning with Dual-level Noisy Correspondence for Multi-modal Entity Alignment, Haobin Li, Yijie Lin, Peng Hu, Mouxing Yang, Xi Peng | 中文简介 | Code

• [ICLR’26] (Oral) Uncover Underlying Correspondence for Robust Multi-view Clustering, Haochen Zhou, Guofeng Ding, Mouxing Yang, Peng Hu, Yijie Lin^†, Xi Peng^† | Code

• [AAAI’26] (Oral) Mamba-Driven Multi-View Discriminative Clustering via Global-Local Cross-View Sequence Modeling, Yuanyang Zhang, Xinhang Wan, Chao Zhang, Jie Xu, Cunjian Chen, Tien-Tsin Wong, Li Yao^†, Yijie Lin^† | Code

• [AAAI’26] Endowing Vision-Language Models with System 2 Thinking for Fine-grained Visual Recognition, Yutong Yang, Lifu Huang, Yijie Lin, Xi Peng, Mouxing Yang | Code

• [Nature Communications’25] MetaQ: fast, scalable and accurate metacell inference via single-cell quantization, Yunfan Li, Hancong Li, Yijie Lin, Dan Zhang, Dezhong Peng, Xiting Liu, Jie Xie, Peng Hu, Lu Chen, Han Luo, Xi Peng | Code

• [TPAMI’25] Community-aware Multi-view Representation Learning with Incomplete Information, Haobin Li, Yijie Lin, Peng Hu, Mouxing Yang, Xi Peng | Code

• [AAAI’25] Incomplete Multi-view Clustering via Diffusion Contrastive Generation, Yuanyang Zhang*, Yijie Lin*, Weiqing Yan, Li Yao, Xinhang Wan, Guangyuan Li, Chao Zhang, Guanzhou Ke, Jie Xu | Code

• [NeurIPS’24] Robust Contrastive Multi-view Clustering against Dual Noisy Correspondence, Ruiming Guo, Mouxing Yang, Yijie Lin, Xi Peng, Peng Hu | Code

• [AAAI’24] Decoupled Contrastive Multi-view Clustering with High-order Random Walks, Yiding Lu, Yijie Lin, Mouxing Yang, Dezhong Peng, Peng Hu, Xi Peng | Code

• [Vicinagearth’24] A survey on deep clustering: from the prior perspective, Yiding Lu, Haobin Li, Yunfan Li, Yijie Lin, Xi Peng | 中文简介

• [arXiv’26] A Multimodal Agentic Pathology Co-pilot via Evidence Grounded Reasoning, Zhe Xu, Zhengyu Zhang, Zhiyuan Cai, Jiahao Xu, Yijie Lin, Ziyi Liu, Junlin Hou, Hongyi Wang, Yuxiang Nie, Yihui Wang, Jiabo Ma, Ling Liang, Yingxue Xu, Zhengrui Guo, Guanghao Wu, Danyi Li, Ziqi Zhou, Donglin Tan, Zhijian Cen, Ying Tan, Xiaolin Liu, Qi Xie, Xiaoying Tang, Xi Peng, Cheng Deng, Lijuan Qu, Ronald Cheong Kin Chan, Li Liang, Hao Chen

🙋 Service

• Journal Reviewer: IEEE TPAMI, IEEE TIP, IEEE TOIS, IEEE TDSC, IEEE TKDE, IEEE TNNLS, and more.

• Conference Area Chair/Reviewer: ICLR, NeurIPS, ICML, CVPR, ICCV, ECCV, ACL, AAAI, ACMMM, and more.