Avatar

Zijie Geng

PhD Student


zijiegeng@miralab.ai

Interests

  • Learning to Optimize
  • AI4Science
  • Graph Generation
  • Reinforcement Learning

Education

  • B.S., Applied Mathematics, School of the Gifted Young, 2022

    University of Science and Technology of China

About me

I am currently a PhD student in USTC. My advisor is Prof. Jie Wang, who leads the MIRA Lab. My research interests include learning to optimize, AI4Science, graph generation, and reinforcement learning.

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

  • Intern at Noah’s Ark Lab, Huawei Technologies, 2023/08 -
  • Intern at MSRA, 02/2022 - 12/2022
  • Nanjing Truezir Software Technology Co., Ltd., Stockholder & Supervisor, 11/2020 - Present
  • Zhejiang Yingyang Asset Management Co., Ltd., Quantitative Analyst, 10/2020 - 04/2021

Publications

Zijie Geng, Jie Wang, Ziyan Liu, Siyuan Xu, Zhentao Tang, Mingxuan Yuan, Jianye Hao, Yongdong Zhang, Feng Wu. Reinforcement Learning within Tree Search for Fast Macro Placement. ICML 2024.

Hong Wang, Zhongkai Hao, Jie Wang, Zijie Geng, Zhen Wang, Bin Li, Feng Wu. Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling (Spotlight). ICLR 2024.

PDF

Zijie Geng, Xijun Li, Jie Wang, Xiao Li, Yongdong Zhang, Feng Wu. A Deep Instance Generative Framework for MILP Solvers Under Limited Data Availability (Spotlight). NeurIPS 2023.

PDF Code

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.

PDF Code

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. KDD 2022.

PDF Code