Pave-GRPO: Beyond Instantaneous Guidance through Principled Average Velocity Decomposition 文章

ArXiv CS.CV2026-06-02NEWSen作者: Pengyang Ling, Jiazi Bu, Yujie Zhou, Yibin Wang, Zhenyu Hu, Zihan Zhang, Yi Jin, Huaian Chen, Yuhang Zang
查看原文 →
关系图谱

Pave-GRPO: Beyond Instantaneous Guidance through Principled Average Velocity Decomposition · 相关技术

相关技术

Principled average velocity decompositionFlow-based generative modelsPave-GRPOGRPOGroup Relative Policy Optimization