M³KG-RAG improves multimodal reasoning in large language models by constructing multi-hop knowledge graphs and selectively pruning retrieved context with GRASP.
LLaV A-neXT- interleave: Tackling multi-image, video, and 3d in large mul- timodal models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation
M³KG-RAG improves multimodal reasoning in large language models by constructing multi-hop knowledge graphs and selectively pruning retrieved context with GRASP.