iADD: Improving Alignment and Diversity in Diffusion Policy Optimization
iADD improves the alignment-diversity tradeoff in diffusion-model post-training using incremental Feynman-Kac updates.
1 stories, newest first · one card per story
iADD improves the alignment-diversity tradeoff in diffusion-model post-training using incremental Feynman-Kac updates.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views