Pith. sign in

Incentivizing multimodal reasoning in large models for direct robot manipulation,

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 Action Priors for Cross-embodiment Robot Manipulation

cs.RO · 2026-06-24 · unverdicted · novelty 5.0

A two-stage framework pretrains an action module with temporal motion priors from unconditioned trajectories using flow-matching, then transfers it to VLA training via decoder reuse and distillation, yielding better performance on cross-embodiment tasks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Learning Action Priors for Cross-embodiment Robot Manipulation cs.RO · 2026-06-24 · unverdicted · none · ref 41

    A two-stage framework pretrains an action module with temporal motion priors from unconditioned trajectories using flow-matching, then transfers it to VLA training via decoder reuse and distillation, yielding better performance on cross-embodiment tasks.