InternLM/Visual-ERM

Official Implementation of "Visual-ERM: Reward Modeling for Visual Equivalence"

23
/ 100
Experimental

This tool helps developers and AI model trainers improve how well their AI models reproduce structured visual content like charts, tables, or SVG graphics. It takes an original image and an image rendered from the model's generated code, then precisely identifies and describes visual differences. AI model trainers and developers who work on vision-to-code generative models would use this to refine their models.

Use this if you need fine-grained, interpretable feedback on visual discrepancies when an AI model converts images into structured code, especially where visual layout, alignment, and style are critical.

Not ideal if your primary concern is text-based similarity of code or if you don't need detailed visual error analysis for model refinement.

AI model training generative AI vision-to-code visual data reconstruction model evaluation
No License No Package No Dependents
Maintenance 13 / 25
Adoption 7 / 25
Maturity 3 / 25
Community 0 / 25

How are scores calculated?

Stars

25

Forks

Language

Python

License

Last pushed

Mar 16, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/InternLM/Visual-ERM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.