MiniGPT-v2 adds unique task identifiers to a large language model so one system can perform image description, visual question answering, and visual grounding after three-stage training.
Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to- sequence learning framework
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
MiniGPT-v2 adds unique task identifiers to a large language model so one system can perform image description, visual question answering, and visual grounding after three-stage training.