PRIME W0: Physical Priors from World Models for Embodied Manipulation
PRIME W0: Physical Priors from World Models for Embodied Manipulation
This research presents PRIME W0, a hierarchical conditional flow-matching framework designed to enhance Vision-Language-Action (VLA) models by integrating long-horizon temporal context and hierarchical VLM representations. The system employs three key designs: per-layer KV injection from a pretrained VLM into an Adaptive MoE action expert, dynamics-aware conditioning via asynchronous world-model subgoal-image prediction and a DINOv2 historical-frame semantic bridge, and Action Dynamic Manifold (ADM) flow matching with covariance-structured noise that respects robot kinematic coupling. Trained in four stages including VLM pre-training, DAT/NTP visuomotor pre-training, DiT flow-matching decoder assembly with WM injection, and end-to-end SFT, PRIME W0 achieves state-of-the-art results on LIBERO and real-robot benchmarks, with systematic ablations validating each architectural component.
The paper introduces PRIME W0, a hierarchical conditional flow-matching framework that integrates world model subgoal prediction and VLM knowledge into an adaptive MoE action expert to address temporal context and kinematic coupling in embodied manipulation tasks.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
Source：arXiv Robotics — research abstracts · arxiv.org