cv

Click the button above to download my full CV.

Basics

Name Bowen Fang
Label PhD Student
Email bf2504@columbia.edu
Phone 917-293-3109
Url https://bwfbowen.github.io/
Summary I study how learning systems discover useful structure, search meaningfully, and build competence in huge sparse-signal spaces.

Work

Education

  • 2024 - present
    Ph.D.
    Columbia University, New York, NY
  • 2022 - 2023
    M.S.
    Columbia University, New York, NY
    Operations Research
  • 2018.09 - 2022.07
    Bachelor
    Peking University, Beijing, China
    Big Data Management and Applications, Minor in Economics

Awards

Skills

Languages
Python
C++
SQL
MATLAB
ML & RL
JAX
PyTorch
TensorFlow
Hugging Face
vLLM
VeRL
Ray/RLlib
Acme
mctx
OpenSpiel
Data & Infra
NumPy
Pandas
SciPy
scikit-learn
XGBoost
Apache Spark
Docker
Kubernetes
Slurm
Airflow
Cloud & Tools
AWS
GCP
Linux
Git

Interests

Learning systems
How learning systems discover useful structure, search meaningfully, and build competence in huge spaces with sparse signal and minimal useful prior structure
Post-training behavior
Understanding the behaviors behind post-training algorithms for large models
System resilience
Evaluating and improving system resilience under uncertainty, stress, and distribution shift

Projects

  • 2025 - Present
    VeRL-Tune
    Scalable HPO and evaluation pipeline integrating VeRL with Ray Tune for agentic RL/LLM reasoning.
  • 2024 - Present
    SINA
    Offline indoor AR evacuation system requiring no network, Bluetooth, or stored maps on the Phone.
  • 2023 - Present
    Muax
    JAX/TF MuZero implementation bridging DeepMind's MCTX with Acme.