Yinjie Wang

photo.png
About Me

I am a Phd student in UChicago. My research interest turns to AI this year, across language models, GUI agent and their reinforcement learning methods.

Before that, I graduated from the School of the Gifted Young at USTC, where I majored in Mathematics.

I prefer fully open-sourced AI projects, see my RL framework for diffusion language models, dLLM-RL, and co-evolving RL framework for LLM coding agents, CURE.

Selected Projects

2025

  1. Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
    Yinjie Wang, Ling Yang, Bowen Li, and 3 more authors
    ICLR 2026, Gave talk at DeepMind & NVIDIA
  2. Co-evolving LLM Coder and Unit Tester via Reinforcement Learning
    Yinjie Wang, Ling Yang, Ye Tian, and 2 more authors
    Neurips 2025 Spotlight
  3. Automated Hierarchical Graph Construction for Multi-source Electronic Health Records
    Yinjie Wang, Doudou Zhou, Yue Liu, and 2 more authors
    Gave talk at Harvard University