SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics 文章

ArXiv CS.CL2026-05-28NEWSen作者: Haolong Hu, Hanyu Li, Tiancheng He, Huahui Yi, An Zhang, Qiankun Li, Kun Wang, Yang Liu, Zhigang Zeng
查看原文 →
关系图谱

SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics · 相关技术

相关技术

LLMTCSRTrajectory-Consistent Summative RewardGRPOSaFeR-Steer