About Me
I was a PhD student at UChicago, but I recently left to devote myself to building interesting things.
Before that, I graduated from the School of Gifted Young at USTC, ranking first in Statistics.
I love open-source projects during PhD. OpenClaw-RL 
is the first project to turn your agents’ daily usage into real-time RL training. dLLM-RL 
is the first open-source post-training framework for DLMs. My research has been supported by ByteDance Seed, Thinking Machines, and Fireworks AI during my PhD.
-
OpenClaw-RL: Train Any Agent Simply by Talking
Yinjie Wang, Xuyang Chen, Xiaolong Jin, and 2 more authors
Real-time RL & RL for digital Agents
-
RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System
Yinjie Wang, Tianbao Xie, Ke Shen, and 2 more authors
ICML 2026
-
Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
Yinjie Wang, Ling Yang, Bowen Li, and 3 more authors
ICLR 2026
-
Co-evolving LLM Coder and Unit Tester via Reinforcement Learning
Yinjie Wang, Ling Yang, Ye Tian, and 2 more authors
Neurips 2025 Spotlight
-
MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation
Ye Tian, Ling Yang, Jiongfan Yang, and 10 more authors
ICLR 2026
-
Variational Co-Evolution via Reinforcement Learning
Qiahao Zheng, Hancong Jin, Junbo Niu, and 3 more authors
COLM 2026
-
Reinforcement Learning for Multimodal Diffusion Language Models via Bidimensional Trajectory and Thought Optimization
Bowen Li, Yinjie Wang, Yunzhi Zhang, and 5 more authors
ECCV 2026
-
Nonparametric Inference for Balance in Signed Networks
Yinjie Wang*, Xuyang Chen*, and Weijing Tang
Biometrika 2026
Reinforcement Learning for Multimodal Diffusion Language Models via Bidimensional Trajectory and Thought OptimizationECCV 2026
