Skip to main content
Loading research indexW

Technical Report: One-Step Drifting Action Heads for GR00T N1.7

arxiv-cs.RO2026-09-16Abstract screenedOpen source ↗
INVESTOR TAKEAWAY

One-step action generation can substantially reduce the inference cost of vision-language-action (VLA) policies, but its effect on closed-loop task success remains an open question. This technical report studies a GR00T N1.

ORIGINAL PAPER

Technical Report: One-Step Drifting Action Heads for GR00T N1.7

WHAT WE KNOW

7 variant in which the iterative diffusion-transformer action head is replaced by a one-step drifting action head, together with an overlap-conditioned extension for asynchronous chunk replacement. All multi-seed drifting runs were trained on two NVIDIA A800 GPUs. On LIBERO, the action head reduces the mean model-forward time of the action head from approximately $45.

WATCH NEXT

Review the primary source, validate the main result, and establish whether any listed-company transmission is direct.

EVIDENCE

What the evidence supports so far

Research signals

VLA

manipulation

What remains unverified

The full methodology, effect size, and limitations still require analyst review.

Company impact remains unverified until a direct economic transmission is established.