AK@_akhaliq · X54
AI 摘要
叛逆学生 通过逆向教师信号进行推理探索 结合自蒸馏的RLVR方法
Rebellious Student
Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR
AK@_akhaliq54
AI 摘要
叛逆学生 通过逆向教师信号进行推理探索 结合自蒸馏的RLVR方法
Rebellious Student
Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR
AK@_akhaliq · X在 X 查看原推x.com