SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation
arXiv:2604.05656v1 Announce Type: new
Abstract: Vision-Language-Action (VLA) models based on flow matching — such as pi0, pi0.5, and SmolVLA — achieve state-of-the-art generalist robotic manipulation, yet their iterative denoising, typically 10 ODE …