On-Policy Distillation for Vision-Language Model Adaptation, an Effective Paradigm on Low-Quality Multimodal Data
OnPoKD is the first framework that applies on-policy distillation to vision-language model adaptation by learning target construction as a policy decision, and is the first framework that applies on-policy distillation to vision-language model adaptation by learning target construction as a policy decision.
Hong-Yuan Zhang, Xian-Da Guo, Yan-Lun Peng et al.
· Information Fusion · 0 citations