JIN HUANG

University of Michigan, Ann Arbor. huangjin@umich.edu

Hi! I am Jin Huang, a Ph.D. student at the University of Michigan in the Foreseer Group, advised by Prof. Qiaozhu Mei. My research interests include large language models (LLMs) for scientific discovery, data attribution, and graph machine learning.

Previously, I completed bachelor’s degrees at the University of Michigan, Ann Arbor, and Shanghai Jiao Tong University. I’ve also had the privilege of working with Prof. Jiaqi Ma and Prof. Danai Koutra. I interned at DP Technology and Intel.

In my free time, I enjoy watching movies. As Edward Yang put it, “we live three times as long since man invented movies.” I owe my gratitude to the late-night series at the State Theatre.

News

Jun 3, 2024 Our paper Can LLMs Effectively Leverage Graph Structural Information: When and Why is accepted to Transactions on Machine Learning Research (TMLR)!
Apr 26, 2023 Our paper HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation is accepted as poster in International Conference on Machine Learning (ICML 2023)! See you at Honolulu, Hawai’i this summer!
Dec 8, 2022 Our paper Graph Learning Indexer: A Contributor-Friendly and Metadata-Rich Platform for Graph Learning Benchmarks is accepted as oral presentation in Learning on Graph conference (LoG 2022)!

Selected Publications

  1. SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding
    Sihang Li*, Jin Huang*, Jiaxi Zhuang, Yaorui Shi, Xiaochen Cai, Mingjun Xu, Xiang Wang, Linfeng Zhang, Guolin Ke, and Hengxing Cai
    Foundation Models for Science Workshop, NeurIPS, 2024
  2. TMLR
    Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?
    Jin Huang, Xingjian Zhang, Qiaozhu Mei, and Jiaqi Ma
    Transactions on Machine Learning Research, 2024