Skip to main content
Search

# Euler Sampling

1 related articles

Subscribe to updates
  1. arXiv

    Euler step counts for flow-matching policies need more than endpoint error: a frozen π0.5 checkpoint shows no sampled stability violation across 30 inputs

    Flow-matching robot policies usually fix their Euler step count from offline endpoint-accuracy sweeps, yet each policy input plus noise draw traces a different noise-to-action path, so trajectory accuracy and local stability can demand different step counts. An exact two-coordinate system and six controlled trained flow models show the two requirements can separate while the learned transport stays unchanged. On a frozen π0.5-LIBERO checkpoint, no sampled contracting mode violated the Euler non-expansion condition across 30 policy inputs; five paired inputs needed 4–9 Euler steps at 5% terminal error and 87–112 at 1%.

You’re all caught up