I am a Ph.D. student in the College of Computer Science at Sichuan University, advised by Prof.Xi Peng.

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

  • i) Robust Multi-modal Learning: I have worked extensively on tackling challenges such as modality missing (CVPR’21, TPAMI’22, AAAI’24-25) and noisy correspondence (ICCV’23, ICLR’24, NeurIPS’24) in image/video-text and image-image data. For a comprehensive overview of our work and insights on noisy correspondence, you can explore our repository Noisy Correspondence Summary.
  • ii) Interactive Multi-modal Learning: I believe the future of multi-modal learning to center around interactions—between users, tools, and external knowledge. Some of my recent work is currently under review.
  • iii) Bioinformatics: My work in this domain focuses on single-cell and multi-omics analysis, tackling key challenges such as representative cell selection (Nature Communications’25) and batch effect correction (TNNLS’23).

I am currently seeking postdoctoral opportunities. If you have any advice or are interested in exploring academic collaborations, please feel free to contact me. I look forward to your insights and suggestions.

🔥 News

  • 2025.01:   One paper about AI4Science was accepted by Nature Communications!
  • 2024.12:   One paper about diffusion clustering was accepted by AAAI Conference on Artificial Intelligence. Congrats to Yuanyang.
  • 2024.06:   We completed a comprehensive survey on deep clustering from the prior perspective. 中文简介
  • 2024.04:   One paper was accepted by IEEE Transactions on Systems, Man and Cybernetics: Systems.
  • 2024.01:   One paper was accepted by International Conference on Learning Representations (ICLR 2024) as oral.
  • 2023.12:   One paper was accepted by AAAI Conference on Artificial Intelligence (AAAI 2024). Congrats to Yiding.
  • 2022.08:   One paper was accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).

📝 Publications

sym

[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 | Project

PWC

PWC

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

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

sym

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

Video | 中文简介 | 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

sym

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

Video | 中文简介 | Code

PWC

  • Reveal bi-level (node- and edge-level) noisy correspondence challenge.
  • This work is included by famous open-source graph matching project ThinkMatch GitHub stars

🎖 Honors and Awards

  • 2024.12 Tencent Scholarship (Outstanding award at SCU)
  • 2023.10 National Scholarship (PhD student)
  • 2022.11 Huawei Scholarship (First prize at SCU)
  • 2019.09 National Scholarship (Undergraduate, Top 1%)

🙋 Service

  • Journal Reviewer: IEEE TIP, IEEE TKDE, IEEE TNNLS, IEEE TAI, and more.

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