pith. sign in

Riemannian flow matching policy for robot motion learning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.RO 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Learning Native Continuation for Action Chunking Flow Policies

cs.RO · 2026-02-13 · unverdicted · novelty 6.0

Legato trains flow-based VLA policies with schedule-shaped action-noise mixtures and randomized conditions to achieve smoother trajectories and ~10% faster task completion than real-time chunking across five real-world manipulation tasks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Learning Native Continuation for Action Chunking Flow Policies cs.RO · 2026-02-13 · unverdicted · none · ref 10

    Legato trains flow-based VLA policies with schedule-shaped action-noise mixtures and randomized conditions to achieve smoother trajectories and ~10% faster task completion than real-time chunking across five real-world manipulation tasks.