VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation
By Kangning Zhang · Paper · cs.CV
Multimodal on-policy distillation (OPD) transfers fine-grained visual knowledge by supervising student-generated trajectories with a privileged-view teacher. Yet its next-token corrections are source-mixed, combining visual signals with linguistic priors and teacher-specific effe