@article{hu2026reinforcezero,
  title   = {REINFORCE Zero: Kernel Alignment Unlocks Stable
             Asynchronous RL with Importance Sampling},
  author  = {Hu, Jian and Zhang, Hao and Zhang, Yifan and Xu, Binfeng
             and Shen, Ao and Zhang, Shaokun and Zou, Yunheng
             and Bai, Yan and Kautz, Jan and Dong, Yi},
  year    = {2026},
  url     = {https://github.com/hijkzzz/REINFORCE-Zero}
}
