mR2AG adds two reflection steps to multimodal LLMs, adaptive retrieval and evidence relevance scoring, yielding SOTA results on INFOSEEK and Encyclopedic-VQA.
How (not) to ensemble lvlms for vqa
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
mR$^2$AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQA
mR2AG adds two reflection steps to multimodal LLMs, adaptive retrieval and evidence relevance scoring, yielding SOTA results on INFOSEEK and Encyclopedic-VQA.