Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
sergiopaniegoΒ 
posted an update 9 days ago
Post
1322
This summer TRL leveled up for multimodal alignment 🌞

βœ… New VLM alignment methods (MPO, GRPO, GSPO)
βœ… Extended RLOO & Online DPO for VLMs
βœ… Native SFT support
βœ… Ready-to-use training scripts

πŸ”— https://huggingface.co/blog/trl-vlm-alignment
In this post