Jinpei Guo

EXPLORE THE POSSIBILITY OF AI


Read More
About

Jinpei Guo

Hi, there! I am Jinpei Guo, a fourth-year undergraduate student in Computer Science and Technology atShanghai Jiao Tong University.

I worked closely with Prof.Junchi Yanas a research assistant atSJTU-ReThinkLab. We developed methods to facilitate the accuracy and efficiency of machine learning models on combinatorial optimization problems. We applied language models and generative models to graph matching, travelling salesman problem, maximum indepent set, etc. I also did research with Prof.Xujie SiatUniversity of Torontoon Neural Logical Reasoning. We developed reliable and interpretable frameworks to capture the rules of logical puzzles explicitly. We conducted research on machine learning for SAT solving as well, especially with GNNs.

My research interests lie at the intersection of machine learning and combinatorial optimization. I am also interested in making the black-box reasoning or decision-making process explainable and reliable by analyzing the model structure and inference process from a mathematical perspective, or combining the machine learning models with exact solvers.


Contact Me

Email: jinpeig@andrew.cmu.edu

GitHub:jp-guo

Publications

OptCM: The Optimization Consistency Models for Solving Combinatorial Problems in Few Shots

Yang Li*, Jinpei Guo*, Runzhong Wang, Hongyuan Zha, Junchi Yan

Neural Information Processing Systems (NeurIPS), 2024


Paper   -  Code

GMTR: Graph Matching Transformers

Jinpei Guo, Shaofeng Zhang, Runzhong Wang, Chang Liu, Junchi Yan

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024


Paper   -  Code

From Distribution Learning in Training to Gradient Search in Testing for Combinatorial Optimization

Yang Li, Jinpei Guo, Runzhong Wang, Junchi Yan

Neural Information Processing Systems (NeurIPS), 2023


Paper   -  Code

Learning Reliable Interpretations with SATNet

Zhaoyu Li, Jinpei Guo, Yuhe Jiang, Xujie Si

Neural Information Processing Systems (NeurIPS), 2023


Paper   -  Code

G4SATBench: Benchmarking and Advancing SAT Solving with Graph Neural Networks

Zhaoyu Li, Jinpei Guo, Xujie Si

Transactions on Machine Learning Research (TMLR)


Paper   -  Code

Education

Shanghai Jiao Tong University, Shanghai, China
09/2020 - 06/2024

Honorary Bachelor of Zhiyuan College
Bachelor of Computer Science and Technology

GPA: 91.9/100, Ranking: 5/109

University of Toronto, Toronto, Canada
04/2023 - 09/2023

Summer Research Program
Internship

Ant Group, Shanghai, China
04/2024 - 07/2024

Algorithm Intern

Teaching
  • Teaching assistant of CS0501H - Data Structure (ACM Honors class), 2022, SJTU
    Prof. Yong Yu; Number of students: 48
Selected Awards
  • Chiang Chen Overseas Graduate Fellowship (Awarded to 10 undergraduates in China), 2024

  • SenseTime Scholarship (Awarded to 30 undergraduates in the field of AI in China), 2023

  • Chinese National Scholarship (Top 1% in SJTU), 2022, 2023

  • Shanghai Scholarship (Top 2% in SJTU), 2021

  • Zhiyuan Honorary Scholarship, 2021, 2022, 2023