Skip to main content
Search

# PlanDiv

1 related articles

Subscribe to updates
  1. arXiv

    More robot-policy samples stop paying off fast: PlanDiv splits candidates by latent plan, lifting CALVIN five-task chains from 56.9% to 69.9%

    Test-time scaling for vision-language-action policies usually resamples one decoder and executes the best candidate, but those candidates differ only by noise: on CALVIN, going from four to eight adds just 0.06–0.07 completed tasks. PlanDiv changes where candidates come from: a lightweight planner proposes latent plan hypotheses, and a shared masked-diffusion executor decodes one action chunk per plan from a single backbone pass, with the policy executing the chunk its own likelihood ranks highest. With backbone, data and training recipe fixed, eight plan-conditioned candidates raise CALVIN ABCD five-task chain success from 56.9% to 69.9%, while autoregressive, plan-free and same-plan resampling reach at most 64.9%.

You’re all caught up