About me

I am currently a second-year graduate student in Department of Electronic Engineering and Information Science (EEIS) at the University of Science and Technology of China (USTC). Previously, I received my Bachelor’s degree in Mathematics and Applied Mathematics in the School of the Gifted Young (SGY) at USTC in 2022. I am working towards my Ph.D. degree in the MIRA Lab at USTC, under the supervision of Prof. Jie Wang. My current research interests include Graph Generation, AI4Science, and Reinforcement Learning. If you share similar interests or have any inquiries, please feel free to contact me by email.

Education

  • M.S. Candidate, Electronic Engineering and Information Science, University of Science and Technology of China, 2022 -
  • B.S., Mathematics and Applied Mathematics, School of the Gifted Young, University of Science and Technology of China, 2018 - 2022
  • High School, Xuzhou No. 1 Middle School, 2016 - 2018

Research

Research Interests

I have broad research interests, and I have not fully decided where I want to go in the long term. I started my research from reinforcement learning (RL). During my internship in MSRA, I studied molecular generation for drug discovery. After that, I applied the graph generation techniques for learning to optimize (L2O).

Publications

  1. Hong Wang, Zhongkai Hao, Jie Wang, Zijie Geng, Zhen Wang, Bin Li, Feng Wu. “Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling.” ICLR 2024 (Spotlight).
  2. Zijie Geng, Xijun Li, Jie Wang, Xiao Li, Yongdong Zhang, Feng Wu. “A Deep Instance Generative Framework for MILP Solvers Under Limited Data Availability.” NeurIPS 2023 (Spotlight). [paper] [project] [code]
  3. Zijie Geng, Shufang Xie, Yingce Xia, Lijun Wu, Tao Qin, Jie Wang, Yongdong Zhang, Feng Wu, Tie-Yan Liu. “De Novo Molecular Generation via Connection-aware Motif Mining.” ICLR 2023. [paper] [code]
  4. Rui Yang, Jie Wang, Zijie Geng, Mingxuan Ye, Shuiwang Ji, Bin Li, Feng Wu. “Learning task-relevant representations for generalization via characteristic functions of reward sequence distributions.” SIGKDD 2022. [paper] [code]

Preprint

  1. Xijun Li, Fangzhou Zhu, Hui-Ling Zhen, Weilin Luo, Meng Lu, Yimin Huang, Zhenan Fan, Zirui Zhou, Yufei Kuang, Zhihai Wang, Zijie Geng, Yang Li, Haoyang Liu, Zhiwu An, Muming Yang, Jianshu Li, Jie Wang, Junchi Yan, Defeng Sun, Tao Zhong, Yong Zhang, Jia Zeng, Mingxuan Yuan, Jianye Hao, Jun Yao, Kun Mao. “Machine Learning Insides OptVerse AI Solver: Design Principles and Applications.” [paper]
  2. Jie Wang, Zijie Geng, Xijun Li, Jianye Hao, Yongdong Zhang, Feng Wu. “G2MILP: Learning to Generate Mixed-Integer Linear Programming Instances for MILP Solvers.” [paper]
  3. Jie Wang, Rui Yang, Zijie Geng, Zhihao Shi, Mingxuan Ye, Qi Zhou, Shuiwang Ji, Bin Li, Yongdong Zhang, Feng Wu. “Generalization in Visual Reinforcement Learning with the Reward Sequence Distribution.” [paper]

Services

  • Conference Reviewer: KDD 2023, NeurIPS 2023 (Top Reviewer), AAAI 2024, ICLR 2024, ICML 2024.

Awards

  • MSRA Stars of Tomorrow, 2022
  • S.-T. Yau College Student Mathematics Contest (Analysis and Partial Differential Equations), Outstanding Prize, 2021
  • The Chinese Mathematics Competitions (CMC), First Price in Anhui Province, 2020
  • S.-T. Yau College Student Mathematics Contest (Applied and Computational Mathematics), Outstanding Prize, 2020

Experience

Interests

  • Texas Hold’em Poker. I find it so fun, though I don’t play well. I am trying to learn GTO theory. I also like some other board games like Guandan and Legends of the Three Kingdoms.
  • Chinese chess. I used to practice Chinese chess for several years. Now I play occasionally, but not as well as I used to.
  • Mathematics. When I was young, I dreamed of becoming a mathematician. Soon I found out that I was not good at math. However, I still want to say I love mathematics.
  • Debating. I was the team leader of the debate team of School of Gifted Young. But I gave up when I started research.
  • Making new friends. So welcome to contact me!