The exceptionally rapid development of highly flexible, reusable artificial intelligence (AI)
models is likely to usher in newfound capabilities in medicine. We propose a new paradigm�…

ChatGPT, an artificial intelligence generated content (AIGC) model developed by OpenAI,
has attracted world-wide attention for its capability of dealing with challenging language�…

The cost of vision-and-language pre-training has become increasingly prohibitive due to
end-to-end training of large-scale models. This paper proposes BLIP-2, a generic and�…

Instruction tuning large language models (LLMs) using machine-generated instruction-
following data has been shown to improve zero-shot capabilities on new tasks, but the idea�…

We present QLoRA, an efficient finetuning approach that reduces memory usage enough to
finetune a 65B parameter model on a single 48GB GPU while preserving full 16-bit�…

Language is essentially a complex, intricate system of human expressions governed by
grammatical rules. It poses a significant challenge to develop capable AI algorithms for�…

The recent GPT-4 has demonstrated extraordinary multi-modal abilities, such as directly
generating websites from handwritten text and identifying humorous elements within�…

Large language models (LLMs) have demonstrated impressive capabilities, but the bar for
clinical applications is high. Attempts to assess the clinical knowledge of models typically�…

We introduce PaLM 2, a new state-of-the-art language model that has better multilingual and
reasoning capabilities and is more compute-efficient than its predecessor PaLM. PaLM 2 is�…

Solving complicated AI tasks with different domains and modalities is a key step toward
artificial general intelligence. While there are numerous AI models available for various�…