GRPO-TTA: Test-Time Visual Tuning for Vision-Language Models via GRPO-Driven Reinforcement Learning 文章

ArXiv CS.CV2026-06-02NEWSen作者: Yujun Li, Hongyuan Zhang, Yuan Yuan
查看原文 →
关系图谱

GRPO-TTA: Test-Time Visual Tuning for Vision-Language Models via GRPO-Driven Reinforcement Learning · 相关技术

相关技术

Test-time adaptationGroup Relative Policy Optimization for Test-Time AdaptationTTAGRPOGRPO-TTAGroup Relative Policy Optimization