Internalizing Agent Experience into Diffusion Model Weights via On-Policy Context Distillation
D-OPCD distills a text-to-image agent harness into diffusion weights, lifting scores from 60.52 to 65.09.
1 stories, newest first · one card per story
D-OPCD distills a text-to-image agent harness into diffusion weights, lifting scores from 60.52 to 65.09.
Today 1.6K readers · 2.4K views · 774 reads · all time 189K views