CV

Please use the button on the right to download the pdf version if needed.

Basics

Name Shouren Wang
Label Computer Science Researcher
Email sxw992@case.edu
Phone 929-302-1790
Url https://wangshourenwsr.github.io
Summary A Ph.D. student in Computer Science, specializing in Machine Learning, creative AI, and Large Language Models.

Education

  • 2024.08 - Present

    Cleveland, OH

    PhD
    Case Western Reserve University
    Computer Science
  • 2021.09 - 2023.05

    Brooklyn, NY

    Master of Science
    New York University
    Computer Engineering
  • 2015.09 - 2019.06

    Changsha, China

    Bachelor of Engineering
    Hunan University
    Digital Media Technology (a computer vision, human-computer interaction and video game specialized Software Engineering)

Work

  • 2023.08 - 2024.07
    Research Intern
    NYU Game Innovation Lab
    Explored the research and methods for creative AI for video games, specifically focusing on developing game-play agents.
    • Developed a PPO-based agent for Street Fighter II using deep reinforcement learning
    • Extended Stable-Baselines3 to support auxiliary objectives and multi-modal inputs
  • 2022.09 - 2023.05
    M.S. Lab Member
    NYU CAN Lab
    Worked on a master project exploring Sensorimotor Control and Reinforcement Learning methods.
    • Proposed a state-augmentation mechanism to explain CNS's adaptability
  • 2019.05 - 2020.09
    Research and Development Engineer
    AsiaInfo Technology
    Worked as a QA group member on the CTDI (EDR) project, focusing on performance testing and enhancement.
    • Improved project efficiency by optimizing server and probe performance
  • 2016.07 - 2016.08
    Research Technician
    Institute of Computing Technology, Chinese Academy of Sciences
    Developed a computer vision algorithm using MATLAB and Locality Sensitivity Hashing to retrieve similar images from a large dataset.

Projects

  • 2024.09 - Present
    Longctx Benchmark V2 for Large Language Models
    Developing an advanced benchmark of long-context capable approaches for large language models.
  • 2023.09 - Present
    Fancy Play Agent
    Developed a PPO Deep Reinforcement Learning model as a game-play agent for Street Fighter II. Extended Stable-Baselines3 to support auxiliary objectives and multi-modal inputs.
    • Designed curriculum learning for improving agent performance
  • 2022.09 - 2023.05
    Simulation for Sensorimotor Control
    Proposed a state-augmentation mechanism to explain the CNS's ability to adapt to unknown system dynamics in a force field.
  • 2023.02 - 2023.05
    Majorization Method for Sparse Logistic Regression
    Applied Majorization methods to calculate the quadratic upper bound for the log-likelihood objective function with L1 norm and compared optimization techniques.

Publications

Skills

Programming Languages
Python
Java
MATLAB
C++
Libraries/Frameworks
PyTorch
Stable-Baselines3
OpenAI Gym
scikit-learn
NumPy
SciPy
pandas
Unity 3D
Developer Tools
Git
Slurm
VS Code
Jupyter Notebook