Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
AdinaY 
posted an update 14 days ago
Post
1778
MAYE🎈a from-scratch RL framework for Vision Language Models, released by GAIR - an active research group from the Chinese community.

✨Minimal & transparent pipeline with standard tools
✨Standardized eval to track training & reflection
✨Open Code & Dataset

Code:
https://github.com/GAIR-NLP/MAYE?tab=readme-ov-file
Dataset:
ManTle/MAYE
Paper:
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme (2504.02587)
martineden

I hope this will be integrated into trl soon..

In this post