Preprint2023
LLaVA 1
Unknown
LLaVA connects CLIP and Vicuna via end-to-end training on GPT-4-generated instruction-following data from image-text pairs.
0Apr 1, 2023MultimodalInstruction Tuning
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
LLaVA connects CLIP and Vicuna via end-to-end training on GPT-4-generated instruction-following data from image-text pairs.
Unknown
Vicuna fine-tunes a 13B LLaMA model on user-shared conversations from ShareGPT to produce more detailed and well-structured answers than Alpaca.