Welcome to my homepage!

I am a senior undergraduate student in Department of Software, Tsinghua University. I am currently working on the research of graph mining under the supervision of Prof. Hanghang Tong at University of Illinois at Urbana-Champaign. Before that, I worked under the supervision of Prof. Quanming Yao at Tsinghua University. I am now also a research intern at KAUST, advised by Prof. Mohamed Elhoseiny.

My research interests include:

• Enhancing the robustness, scalability, and interpretability of graph neural networks.
• Pioneering innovations to accelerate large language model prediction.

News

• [Oct 2024] Grateful to be awarded the National Scholarship! 🎓
• [Oct 2024] Happy to receive the NeurIPS 2024 Travel Award! 🏅
• [Sep 2024] Our paper "DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs" was accepted by NeurIPS 2024 as an oral! 🎉🎉🎉
• [Jun 2024] Happy to receive the ICML 2024 Travel Award! 🏅
• [May 2024] Our paper "SLOG: An Inductive Spectral Graph Neural Network Beyond Polynomial Filter" was accepted by ICML 2024! 🚀

Publications

• DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs.
  Haokun Lin*, Haobo Xu*, Yichen Wu*, Jingzhi Cui, Yingtao Zhang, Linzhan Mou, Linqi Song, Zhenan Sun, Ying Wei.
  The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024. [Oral]
  [Paper] [Code]
• SLOG: An Inductive Spectral Graph Neural Network Beyond Polynomial Filter.
  Haobo Xu*, Yuchen Yan*, Dingsu Wang, Zhe Xu, Zhichen Zeng, Tarek F. Abdelzaher, Jiawei Han, Hanghang Tong.
  Forty-first International Conference on Machine Learning (ICML), 2024.
  [Paper] [Code]
• KGTuner+: Automated and Efficient Hyper-parameter Search for KG Learning.
  Zhanke Zhou, Yongqi Zhang, Haobo Xu, Quanming Yao, Bo Han
  Under Review at TPAMI (IEEE Transactions on Pattern Analysis and Machine Intelligence).
  

Experience

• University of Illinois at Urbana-Champaign, Aug. 2023 - Present
  Research Intern, supervised by Prof. Hanghang Tong
  Towards robust, efficient, and scalable graph kernel & length extrapolation for LLMs.
  
• Tsinghua University, Feb. 2022 - Jun. 2023
  Research Intern, supervised by Prof. Quanming Yao
  Efficient hyper-parameter optimization for knowledge graph models.

Services

• Program Committee/Reviewer: IEEE BigData 2023, AAAI 2024, NeurIPS 2024, AAAI 2025, ICLR 2025, AISTATS 2025.

Awards

• National Scholarship, P.R.China, 2024.
• NeurIPS 2024 Travel Award.
• ICML 2024 Travel Award.
• Comprehensive Excellence Award, Tsinghua University (2021 - 2024).
• First Prize in National Olympiad in Informatics in Provinces (NOIP) of China (2017, 2018).
• First Provincial-level in Chinese Physics Olympiad (2018, 2019).