PathTime-VLA: Path-Time Decoupling for Factorized Post-Training of Vision-Language-Action Policies

Name: PathTime-VLA: Path-Time Decoupling for Factorized Post-Training of Vision-Language-Action Policies
Uploaded: 2026-10-11T20:09:23.312240+00:00
Duration: 297 s
Description: PathTime-VLA introduces a path-time decoupled action representation for Vision-Language-Action policies. It separates geometric guidance from execution timing, allowing distinct post-training interfaces for geometry and speed. This enables a staged learning process where demonstrations set a prior, RL learns execution multipliers, and diffusion refines the path generation.

PathTime-VLA introduces a path-time decoupled action representation for Vision-Language-Action policies. It separates geometric guidance from execution timing, allowing distinct post-training interfaces for geometry and speed. This enables a staged learning process where demonstrations set a prior, RL learns execution multipliers, and diffusion refines the path generation.

Open the full episode