←Backllava-rlhf/LLaVA-RLHF0Copy as MarkdownView on GitHub↗396 stars·31 forks·Python·GPL-3.0·0 viewsllava-rlhf.github.io↗LLaVA RLHFFeaturesAlignment and RLHF - Factually augmented reinforcement learning from human feedback.Hallucination Mitigation - Aligning multimodal models using factually augmented reinforcement learning.Mitigation Methods - Aligns models using factually augmented reinforcement learning.
