Technical Report: One-Step Drifting Action Heads for GR00T N1.7
Abstract
Replacing an iterative diffusion-transformer action head with a one-step drifting action head in a GR00T N1.7 VLA variant reduces inference latency but consistently lowers closed-loop success on LIBERO tasks, indicating a speed–success trade-off.
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 N1.7 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 45.3,ms to 5.0,ms, while the measured backbone-plus-head time falls from approximately 70.0,ms to 30.6,ms. However, this speedup is accompanied by a systematic reduction in task success. Across three drifting seeds, success is 64.0pm4.0% on LIBERO-Spatial, 52.0pm1.0% on LIBERO-Goal, and 26.0pm2.6% on LIBERO-Long. The low seed variance indicates that the degradation is not explained by random initialization alone. We report the result as a speed--success trade-off rather than an overall improvement, and discuss likely contributing factors including deterministic one-step mode averaging, batch-dependent geometry estimation, long open-loop chunk execution, and the fact that synchronous LIBERO evaluation does not exercise the asynchronous overlap path.
Get this paper in your agent:
hf papers read 2609.18108 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 1
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper