arXiv · AI· Huawei Lin, Jinting Liu, Tongyan Wang, Xuyang Chen, Ruihua Shi, Zhichao Xu, Jiaxin Qin, Guoshenghui Zhao, Baijian Yang, Yingjie Victor Chen, Tan Yu, Weijie Zhao·· 3 天前AI 评分45
ViRA 通过跨输入相对策略优化实现超高分辨率视觉智能体
ViRA: Toward Ultra-High-Resolution Visual Agents via Cross-Input Relative Policy Optimization
AI 导读
研究团队提出 Cross-Input Relative Policy Optimization(CrossRPO),用于训练基于对比数据集的视觉智能体,避免依赖常识作答。
来源:arXiv · AI · arxiv.org