Multi-grained concept annotations, when integrated into interleaved image-text documents, improve MLLM comprehension and generation beyond caption-only pretraining at much smaller data scale.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models
Multi-grained concept annotations, when integrated into interleaved image-text documents, improve MLLM comprehension and generation beyond caption-only pretraining at much smaller data scale.