Lin-Jie Mu

CA-OPD: Confidence-Aware On-Policy Distillation for Structured Visual Prediction

Autoregressive vision language models unify heterogeneous perception tasks but are highly susceptible to compounding errors. On-policy distillation (OPD) bridges the training-inference mismatch by training students on their own rollouts. However, unreliable student predictions, especially early in training, can derail...