Vp Vla Visual Prompting Robotics

Replace monolithic VLA single-pathway decision-making with a decomposed System-2/System-1 architecture where a pretrained VLM planner identifies targets as visual prompts (crosshairs, bounding boxes) and a VLA controller executes on grounded observations, improving success rates by 5-8% on manipulation tasks. Use when spatial precision is critical, multi-step reasoning is needed, and you have access to pretrained segmentation and vision-language models.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 3dc5156d55

Frequently asked questions

npx get-skill add adu2021/vp-vla-visual-prompting-robotics