Swapping pooled visual similarity for late-interaction MaxSim in graph-grounded multimodal QA is reported to improve graph-linked image retrieval and QA point estimates on MultimodalQA.
Title resolution pending
1 Pith paper cite this work, alongside 5 external citations. Polarity classification is still indexing.
1
Pith paper citing it
5
external citations · OpenAlex
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ColGraphRAG: Late-Interaction Evidence Retrieval for Multimodal GraphRAG
Swapping pooled visual similarity for late-interaction MaxSim in graph-grounded multimodal QA is reported to improve graph-linked image retrieval and QA point estimates on MultimodalQA.