Hairu Wang

Hairu Wang

Master's student at University of Science and Technology of China

👋 About Me

Hi, everyone! I earned my bachelor’s degree at Harbin Institute of Technology in 2023. In the same year, I joined the School of Computer Science at USTC for my master’s degree. Currently, I am a third-year M.S. candidate jointly supervised by Prof. Xike Xie and Prof. S. Kevin Zhou.

Please don’t hesitate to reach out for any discussion. You can contact me via Email: hrwang00@mail dot ustc dot edu dot cn. I am always open to engaging in intriguing research endeavors! 😊

📝 Research Interests:

My research interests include NNs’ memory, Large Language Models, LLM efficiency, and RAG.

🎯 Teaching NNs to memorize data streams & Learnable Large-Scale Data Compression.

  1. [ICLR 2024 Spotlight] Mayfly: a Neural Data Structure for Graph Stream Summarization. link
  2. [TPAMI 2024] Learning to Sketch: A Neural Approach to Item Frequency Estimation in Streaming Data. link
  3. [ICML 2025] Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams. link

🎯 LLM Efficiency.

  1. [EMNLP 2024 Main] Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging. link
  2. [EMNLP 2025 findings] SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness. link

🎯 RAG in LLMs.

  1. [ACL 2025 findings] FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs link
  2. [arXiv] Path Pooling: Training-Free Structure Enhancement for Efficient Knowledge Graph Retrieval-Augmented Generation. link

📖 Education

  • 2023.09 - 2026.06, Master in Computer Science and Technology, University of Science and Technology of China (USTC).
  • 2019.09 - 2023.06, Bachelor in Software Engineering, Harbin Institute of Technology (HIT).