I am currently a first-year MPhil student at The Hong Kong University of Science and Technology (Guangzhou) in Data Science and Analytics, supervised by Prof. Yuxuan Liang and Prof. Hui Xiong.

My research interests include data mining, recommendation systems, and computer vision.

I hold a B.Eng degree in Computer Science and Technology from Harbin Institute of Technology (Shenzhen), advised by Prof. Miao Zhang. Fortunately, I have also received guidance from Prof. Shanshan Feng and Prof. Yongyong Chen.

If you are interested in any form of academic collaboration, please feel free to contact me at sisuolyu@outlook.com.

📝 Publications

ICASSP 2025
sym

Multi-view Hypergraph-based Contrastive Learning Model for Cold-Start Micro-video Recommendation (Lecture)
Sisuo Lyu, Xiuze Zhou, and Xuming Hu
[Paper][Code][PPT][Poster]

  • This work proposes MHCR, a novel framework that leverages multi-view hypergraph structures and contrastive learning to address the challenges of over-smoothing and cold-start problems in micro-video recommendation systems by effectively utilizing multimodal features and self-supervised learning signals.
  • ACL 2025 Xiuze Zhou, Jiang Jian, Hong Chen, Junzhuo Li, Sisuo LYU, Zhang Wei, Yuanguo Lin, Xuming Hu, “A Multi-modal Adapter for Explainable Recommendations: Bridging LLMs and Collaborative Filtering” (under review)
  • NeurIPS Workshop 2022 Bizhe Bai, Jie Tian, Tao Wang, Sicong Luo, Sisuo LYU, “YUSEG: Yolo and Unet is all you need for cell instance segmentation”  [Paper][Code]
  • Chinese Computer Software Copyright Sisuo LYU, “Extremely lightweight intelligent voice dialogue system

📈 Academic Competitions

CVPR 2022 Workshop
sym

Image Matching Challenge 2022
Gold medal | 8/642
[Code]

  • This work fused matching results from four models (LoFTR, SuperGlue, DKM, and QuadTreeAttention), and employed Thread PoolExecutor for efficient, multi-threaded inference on key points and F-matrix calculation within the competition’s time constraints.
CVPR 2022 Workshop
sym

Sorghum -100 Cultivar Identification - FGVC 9
3/252
[Code]
[Plog]

  • This work utilized histogram equalization to improve image quality while employing IBN-Net integrates instance normalization (IN) and batch normalization (BN), bolstering model learning capacity and generalization to address competition challenges. Implementing ArcFace enhances the model’s discriminative ability for superior performance.
CCF BDCI 2021
sym

System Certification Risk Prediction
National First Prize | 1/1143
[Code]

  • This work leverages LightGBM to enhance prediction performance, extracting crucial time features and improving the model through statistical crossover and categorical feature word embeddings. Employed hierarchical multi-fold cross-validation for superior generalization and applied normalization and fusion methods post-ranking to boost complementary capabilities.

🎖 Honors and Awards

  • 2024.05 “Outstanding Graduate”, Harbin Institute of Technology

  • 2024.03Huawei AI Education Base Scholarship”, Huawei

  • 2023.11 “Outstanding Student Honor”, Harbin Institute of Technology

  • 2023.10 “Academic Scholarship”, Harbin Institute of Technology

  • 2023.04 “Excellent League Member Honor”, Harbin Institute of Technology

  • 2023.03Science and Innovation Star Scholarship”, Sailvan Times

  • 2022.11 “Outstanding Student Honor”, Harbin Institute of Technology

  • 2022.11 “Academic Scholarship”, Harbin Institute of Technology

  • 2021.12 “Outstanding Student Honor”, Harbin Institute of Technology

  • 2021.11 “Academic Scholarship”, Harbin Institute of Technology

📖 Educations

  • 2020.09 - 2024.06, B.Eng. in Computer Science and Technology, Harbin Institute of Technology (Shenzhen)
  • 2024.09 - 2026.07(expected), MPhil in Data Science and Analytics, The Hong Kong University of Science and Technology (Guangzhou)

📮 Contact

  • 📧 Email: sisuolyu@outlook.com
  • 💬 Wechat: sisuolyu