QKVQA proposes a question-focused filtering method with QFF and CDA modules that boosts accuracy by 3.2 points on Encyclopedic-VQA and 2.2 points on InfoSeek over prior state-of-the-art.
Core-mmrag: Cross- source knowledge reconciliation for multimodal rag.arXiv preprint arXiv:2506.02544
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
QKVQA: Question-Focused Filtering for Knowledge-based VQA
QKVQA proposes a question-focused filtering method with QFF and CDA modules that boosts accuracy by 3.2 points on Encyclopedic-VQA and 2.2 points on InfoSeek over prior state-of-the-art.
- R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation