1
EQPO: Equitable Group Relative Policy Optimization for Clinical Reasoning
针对临床推理的公平性优化新方法,EQPO通过分组相对策略强化学习兼顾质量与群体公平,入选NeurIPS旗下Workshop口头报告。
arXiv:2510.19893v2 Announce Type: replace Abstract: Medical AI systems demonstrated impressive diagnostic performance, yet they routinely show uneven …