Boosting RL-Based Visual Reasoning with Selective Adversarial Entropy Intervention 文章

ArXiv CS.AI2026-06-02NEWSen作者: Yang Yu, Zhuangzhuang Chen, Lanqing Li, Xiaomeng Li
查看原文 →
关系图谱

Boosting RL-Based Visual Reasoning with Selective Adversarial Entropy Intervention · 相关人物

暂无数据