Skip to content
#

vlm-as-judge

Star

Here are 2 public repositories matching this topic...

lord-arbiter / Crucible

Star 3

Multi-axis VLM-as-judge data curation for robot demonstrations. Five specialist critics (visual / kinematic / task / strategy / safety) score every LeRobot episode with rationale and timestamp evidence. Model-agnostic — any OpenAI-compatible vision endpoint.

robotics imitation-learning data-quality robot-learning vlm huggingface dataset-curation vision-language-model llm-as-judge lerobot vlm-as-judge behavioral-rubric
  • Updated May 10, 2026
  • Python

Improve this page

Add a description, image, and links to the vlm-as-judge topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the vlm-as-judge topic, visit your repo's landing page and select "manage topics."

Learn more