We introduce LLaVA (L arge L anguage- a nd- V ision A ssistant), an end-to-end trained large multimodal model that connects a vision encoder and LLM for general-purpose visual and …

LLaVA is an open-source project, collaborating with research community to advance the state-of-the-art in AI. LLaVA represents the first end-to-end trained large multimodal model (LMM) that …

With additional scaling to LLaVA-1.5, LLaVA-NeXT-34B outperforms Gemini Pro on some benchmarks. It can now process 4x more pixels and perform more tasks/applications than before.

Apr 17, 2023 · When fine-tuned on Science QA, the synergy of LLaVA and GPT-4 achieves a new state-of-the-art accuracy of 92.53%. We make GPT-4 generated visual instruction tuning data, …

Jun 10, 2025 · A complete technical breakdown of the LLaVA-1.5 multimodal visual assistant. Explore its architecture, open-source training data, and how to use the model.

Model type: LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, …

3 days ago · LLaVA-Interactive is a research prototype system for multimodal AI interaction. The system can engage in multi-round conversations with users by receiving multimodal user input …