Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher

Teacher-free on-policy distillation for flow matching. At each timestep the student’s deterministic next-state prediction is branched into K stochastic SDE candidates, rolled out with an ODE sampler, and scored against a deterministic self-reference to produce normalized advantages. A velocity field is then optimized with an all-branch pull-push objective. Outperforms prior RL and OPD baselines on single and mixed-reward benchmarks without requiring task-specific teachers.