1 result found Sort:

RLHF-V
RLHF-V RLHF-V
6
220
unknown
2
[CVPR'24] RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback
gpt-4 llama rlhf-v chatbot multimodal multi-modality visual-language-learning
Created 2023-11-29
73 commits to main branch, last one 17 days ago