Preprint2023
Florence-2
Unknown
Florence-2 unifies diverse vision tasks under a single sequence-to-sequence model using prompt-based instructions and a massive multitask dataset.
0Nov 1, 2023PromptingComputer Vision
arXiv
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
Florence-2 unifies diverse vision tasks under a single sequence-to-sequence model using prompt-based instructions and a massive multitask dataset.
Pengfei Liu, Weizhe Yuan, Jinlan Fu, et al.
This paper systematically surveys prompt-based learning in NLP, a paradigm where pre-trained language models are adapted to tasks via textual prompts for few-shot or zero-shot learning.