VISTA: Verifier-Informed Student-to-Teacher Adaptation for On-Policy Self-Distillation
Verifier-Informed Student-to-Teacher Adaptation (VISTA), which preserves the standard OPSD student update while using outcome-verified rollouts to adapt the teacher toward the student distribution and demonstrates the value of student supervision from outcome-verified rollouts.
Ze-Wen Ding, Ze-Zhong Wu, Zhou Tao et al.
· 0 citations