[CVPR'25] RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness
-
Updated
Mar 4, 2025 - Python
[CVPR'25] RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness
Align llava-v1.6-mistral-7b on RLAIF-V dataset using ORPO
Add a description, image, and links to the rlaif-v topic page so that developers can more easily learn about it.
To associate your repository with the rlaif-v topic, visit your repo's landing page and select "manage topics."