SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation
Vision-language-action (VLA) models with flow-matching action heads, such as π0 and π0.5, have become a standard recipe for generalist robot manipulation, but every action chunk is produced by integrating a learned velocity field over about ten sequential action-expert evaluations, so action generation dominates model latency and caps the achievable control frequency. Existing remedies either shrink each evaluation through layer distillation or pruning while leaving the sequential solver in place, or import one-step objectives from image generation that were designed for training from scratch, rely on an exponential-moving-average teacher or an external critic, and regress finite-span tar...
| Authors | Wuyang Luan, Junhui Li, Weiguang Zhao et al. |
|---|---|
| Primary category | cs.CV |
| Published | 7 April 2026 |
| Last updated at source | 14 October 2026 |
Connected in the knowledge graph
- Rylinjames/pi05-snapflow-distill-1nfeModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.