Pinned Repositories
LLaVA-RLHF
Aligning LMMs with Factually Augmented RLHF
Large-Scale-Medical
[CVPR 2024 Extension] 160K volumes (42M slices) datasets, new segmentation datasets, 31M-1.2B pre-trained models, various pre-training recipes, 50+ downstream tasks implementation
RLAIF-V
[CVPR'25] RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness
Valley
The official repository of "Video assistant towards large language model makes everything easy"
123
LLaVA-Hound-DPO